Forum Replies Created
-
AuthorPosts
-
FermParticipant
Halle,
The solution for the link you gave me actually helped with this issue. I terminate the voice recognition after 2 sec.
I am still using the background thread that checks the inputLevel and restarts if it doesn’t change. But the number of times that happens now has decreased very much (specially after a running a while when it seemed to happen all the time).
Maybe the terminating the voice recognition lets the buffer “breathe” a little.
FermParticipantThank you very much! I’ll try it out.
FermParticipantI noticed that if I start listening when an other app is playing audio that app stops playing audio. Maybe if we fix that, this issue will be fixed.
What do you think?
FermParticipantI haven’t profiled yet I’m just assuming. It seems unnecessary to keep on recognizing when one already knows, in my case, that it won’t be a match.
Is there a hardcoded maximum length of continuos speech limit? In that case maybe decrease this value.
FermParticipantWhat does pocketsphinxController.outputAudio do?
FermParticipantMy words are short.
I do not want to keep feeding speech into the recognizer. If the speaker talks a long time without silence, will it affect memory consumption, buffer sizes?
FermParticipantNo I am not using audiosession in my code.
I added the following to disable output in ContinousAudioUnit
UInt32 enableOutput = 0;
setEnableIOStatus = AudioUnitSetProperty(audioDriver->audioUnit,
kAudioOutputUnitProperty_EnableIO,
kAudioUnitScope_Output,
0,
&enableOutput,
sizeof(enableOutput));if(setEnableIOStatus != noErr) {
if(openears_logging == 1) NSLog(@”Couldn’t disable IO output: %d”,(int)setEnableIOStatus);
}But then I got “cont_ad_calib failed”
FermParticipantIts the input buffer thats underrun right?
I do not understand how the input is related to AirPlay. If it was the output I would see that it is related. But the input is always the device input, the microphone.Where in the code would I look at the buffers?
FermParticipantOh I understand, thanks.
Will I be notified on this thread when the issue is addressed?
FermParticipantOk.
Here’s the input level in the log. It is not returning zeros, its not being updated.
This time the buffer underrun after pocketsphinxDidDetectSpeech.2012-10-12 18:10:25.963 MyApp[3678:6303] audioCategory is correct, we will leave it as it is.
2012-10-12 18:10:25.964 MyApp[3678:6303] bluetoothInput is correct, we will leave it as it is.
2012-10-12 18:10:25.965 MyApp[3678:6303] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 18:10:25.966 MyApp[3678:6303] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 18:10:25.967 MyApp[3678:6303] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 18:10:25.968 MyApp[3678:6303] Setting the variables for the device and starting it.
2012-10-12 18:10:25.968 MyApp[3678:6303] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 18:10:26.001 MyApp[3678:1703] pocketsphinxInputLevel -115.4957504272
2012-10-12 18:10:26.042 MyApp[3678:6303] Started audio output unit.
2012-10-12 18:10:26.045 MyApp[3678:6303] Listening.
2012-10-12 18:10:26.046 MyApp[3678:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 18:10:26.048 MyApp[3678:6963] -[PDFPresentationView configurePage:forIndex:]0 page index: 6, current 6
2012-10-12 18:10:26.053 MyApp[3678:6963] -[PageScrollView setView:size:] Starting at zoomScale: 0.42, minimumZoomScale: 0.42
2012-10-12 18:10:26.271 MyApp[3678:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 18:10:27.026 MyApp[3678:1703] pocketsphinxInputLevel -114.3440628052
2012-10-12 18:10:28.060 MyApp[3678:1703] pocketsphinxInputLevel -115.1563186646
2012-10-12 18:10:29.065 MyApp[3678:1703] pocketsphinxInputLevel -115.6520004272
2012-10-12 18:10:30.071 MyApp[3678:1703] pocketsphinxInputLevel -114.1130981445
2012-10-12 18:10:31.113 MyApp[3678:1703] pocketsphinxInputLevel -112.4258346558
2012-10-12 18:10:32.136 MyApp[3678:1703] pocketsphinxInputLevel -116.5228881836
2012-10-12 18:10:33.160 MyApp[3678:1703] pocketsphinxInputLevel -117.2090682983
2012-10-12 18:10:34.164 MyApp[3678:6303] Speech detected…
2012-10-12 18:10:34.165 MyApp[3678:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 18:10:34.188 MyApp[3678:1703] pocketsphinxInputLevel -86.3747482300
2012-10-12 18:10:35.231 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:36.274 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:37.317 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:38.355 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:39.398 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:40.437 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:41.458 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:42.491 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:43.528 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:44.552 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:45.584 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:46.586 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:47.627 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:48.662 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:49.698 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:50.741 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:51.784 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
2012-10-12 18:10:52.817 MyApp[3678:1703] pocketsphinxInputLevel -113.3651199341
FermParticipantSo this is not related to AirPlay?
Do you mean I should just print the pocketsphinxInputLevel in a while loop on a background thread?
FermParticipantI meant that the error is caused in relation to an input signal being received after pocketsphinxDidStartListening.
Do you mean that the audio recognizer is not started in the case where (1) happens?Could I set a timer in pocketsphinxDidStartListening and programatically try to start the audio recognizer in no speech is detected after say 1 min?
FermParticipantI do not get any delegate calls after pocketsphinxDidStartListening. Nothing happens.
I do not get fail until I stop and start. So I cannot react to it programmatically.If I react to the “nothing happens” by pressing a ui button manually to stop and start the listening (2) and (3) then I get the crash.
But stopping listening in (5) as a respons to pocketSphinxContinuousSetupDidFail seemed to fix the crash. Thank you.
So I can get it to work again if I manually restart after (1) then wait for it to fail and stop, and then manually start.FermParticipantBut this is regarding why restarting is crashing? And that might be a secondary error following the (1) error that it stops detecting speech.
As long as (1) doesn’t happen I can stop and start how many times I want.
It seems now when I test that if I keep quiet after pocketsphinxDidStartListening then restart, it’s ok. I think the problem arises as input is received.
Btw, you can download AirServer trial to use the computer as an airplay device.
FermParticipantIt’s the latest, downloaded it today. But I think the old version from august was cached. Here’s a new reproduced log.
2012-10-12 16:31:01.510 MyApp[3295:1703] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting
2012-10-12 16:31:01.517 MyApp[3295:1703] Starting OpenEars logging for OpenEars version {{{{1.2.2}}}} on device: iPhone running iOS version: 6.000000
2012-10-12 16:31:01.518 MyApp[3295:1703] A sample rate was requested that isn’t one of the two supported values of 16000 or 8000 so we will use the default of 16000.
2012-10-12 16:31:01.521 MyApp[3295:1703] The audio session has never been initialized so we will do that now.
2012-10-12 16:31:01.524 MyApp[3295:1703] Checking and resetting all audio session settings.
2012-10-12 16:31:01.527 MyApp[3295:1703] audioCategory is incorrect, we will change it.
2012-10-12 16:31:01.531 MyApp[3295:1703] audioCategory is now on the correct setting of kAudioSessionCategory_PlayAndRecord.
2012-10-12 16:31:01.544 MyApp[3295:1703] bluetoothInput is incorrect, we will change it.
2012-10-12 16:31:01.563 MyApp[3295:1703] bluetooth input is now on the correct setting of 1.
2012-10-12 16:31:01.571 MyApp[3295:1703] categoryDefaultToSpeaker is incorrect, we will change it.
2012-10-12 16:31:01.581 MyApp[3295:1703] CategoryDefaultToSpeaker is now on the correct setting of 1.
2012-10-12 16:31:01.585 MyApp[3295:1703] preferredBufferSize is incorrect, we will change it.
2012-10-12 16:31:01.601 MyApp[3295:1703] PreferredBufferSize is now on the correct setting of 0.128000.
2012-10-12 16:31:01.604 MyApp[3295:1703] preferredSampleRateCheck is incorrect, we will change it.
2012-10-12 16:31:01.606 MyApp[3295:1703] preferred hardware sample rate is now on the correct setting of 16000.000000.
2012-10-12 16:31:01.682 MyApp[3295:1703] AudioSessionManager startAudioSession has reached the end of the initialization.
2012-10-12 16:31:01.685 MyApp[3295:1703] Exiting startAudioSession.
2012-10-12 16:31:01.688 MyApp[3295:611b] Recognition loop has started
2012-10-12 16:31:01.690 MyApp[3295:1703] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting finished
INFO: cmd_ln.c(706): Parsing command line:
\
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel \
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic \
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app \
-lw 6.500000 \
-maxhmmpf 3000 \
-samprate 16000Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-argfile
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app
-input_endian little little
-jsgf
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latsize 5000 5000
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel
-lmctl
-lmname default default
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf -1 3000
-maxnewoov 20 20
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-5 1.000000e-05
-pl_window 0 0
-rawlogdir
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-usewdphones no no
-uw 1.0 1.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02INFO: cmd_ln.c(706): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 47 \
-varnorm noCurrent configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 47
-dither no no
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.000000e+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec 0-12/13-25/26-38
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02INFO: acmod.c(250): Parsed model-specific feature parameters from /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/feat.params
INFO: feat.c(713): Initializing feature stream to type: ‘1s_c_d_dd’, ceplen=13, CMN=’current’, VARNORM=’no’, AGC=’none’
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(171): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/transition_matrices
INFO: acmod.c(125): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(995): Loading senones from dump file /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/sendump
INFO: s2_semi_mgau.c(1019): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1114): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1391): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4110 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 3 words read
INFO: dict.c(341): Reading filler dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(400): Building PID tables for dictionary
INFO: dict2pid.c(408): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones
INFO: dict2pid.c(135): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(199): Allocated 30200 bytes (29 KiB) for single-phone word triphones
INFO: ngram_model_arpa.c(488): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa.c(143): Reading unigrams
INFO: ngram_model_arpa.c(528): 4 = #unigrams created
INFO: ngram_model_arpa.c(204): Reading bigrams
INFO: ngram_model_arpa.c(547): 4 = #bigrams created
INFO: ngram_model_arpa.c(548): 3 = #prob2 entries
INFO: ngram_model_arpa.c(558): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(302): Reading trigrams
INFO: ngram_model_arpa.c(573): 2 = #trigrams created
INFO: ngram_model_arpa.c(574): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 2 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 132
INFO: ngram_search_fwdtree.c(338): after: 2 root, 4 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(167): fwdflat: min_ef_width = 4, max_sf_win = 25
2012-10-12 16:31:01.866 MyApp[3295:611b] Starting openAudioDevice on the device.
2012-10-12 16:31:01.868 MyApp[3295:611b] Audio unit wrapper successfully created.
2012-10-12 16:31:01.881 MyApp[3295:611b] Set audio route to AirTunes
2012-10-12 16:31:01.883 MyApp[3295:611b] Checking and resetting all audio session settings.
2012-10-12 16:31:01.886 MyApp[3295:611b] audioCategory is correct, we will leave it as it is.
2012-10-12 16:31:01.888 MyApp[3295:611b] bluetoothInput is correct, we will leave it as it is.
2012-10-12 16:31:01.890 MyApp[3295:611b] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 16:31:01.893 MyApp[3295:611b] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 16:31:01.895 MyApp[3295:611b] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 16:31:01.896 MyApp[3295:611b] Setting the variables for the device and starting it.
2012-10-12 16:31:01.899 MyApp[3295:611b] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 16:31:02.641 MyApp[3295:611b] Started audio output unit.
2012-10-12 16:31:02.647 MyApp[3295:611b] Calibration has started
2012-10-12 16:31:02.648 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStartCalibration] Pocketsphinx calibration has started.
2012-10-12 16:31:04.881 MyApp[3295:611b] Calibration has completed
2012-10-12 16:31:04.882 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidCompleteCalibration] Pocketsphinx calibration is complete.
2012-10-12 16:31:04.885 MyApp[3295:611b] Project has these words in its dictionary:
BACK
NEXT
NEXT(2)2012-10-12 16:31:04.886 MyApp[3295:611b] Listening.
2012-10-12 16:31:04.888 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 16:31:05.585 MyApp[3295:611b] Speech detected…
2012-10-12 16:31:05.587 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 16:31:07.103 MyApp[3295:611b] Stopping audio unit.
2012-10-12 16:31:07.103 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 16:31:07.197 MyApp[3295:611b] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 16:31:07.198 MyApp[3295:611b] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 655 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551): 4811 senones evaluated (62/fr)
INFO: ngram_search_fwdtree.c(1553): 1923 channels searched (24/fr), 148 1st, 1552 last
INFO: ngram_search_fwdtree.c(1557): 824 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 72 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.08 CPU 0.108 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.66 wall 2.132 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 3 words
INFO: ngram_search_fwdflat.c(951): 161 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 3444 senones evaluated (44/fr)
INFO: ngram_search_fwdflat.c(955): 1918 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 259 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 125 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.004 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.007 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .61
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 27 nodes, 24 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:61:76) = -481875
INFO: ps_lattice.c(1405): Joint P(O,S) = -482050 P(S|O) = -175
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 16:31:07.208 MyApp[3295:611b] Pocketsphinx heard “BACK” with a score of (-175) and an utterance ID of 000000000.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
2012-10-12 16:31:07.212 MyApp[3295:611b] Checking and resetting all audio session settings.
2012-10-12 16:31:07.212 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-7318”;
}
)
2012-10-12 16:31:07.216 MyApp[3295:611b] audioCategory is correct, we will leave it as it is.
2012-10-12 16:31:07.218 MyApp[3295:611b] bluetoothInput is correct, we will leave it as it is.
2012-10-12 16:31:07.219 MyApp[3295:611b] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 16:31:07.220 MyApp[3295:611b] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 16:31:07.222 MyApp[3295:611b] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 16:31:07.223 MyApp[3295:611b] Setting the variables for the device and starting it.
2012-10-12 16:31:07.224 MyApp[3295:611b] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 16:31:07.379 MyApp[3295:611b] Started audio output unit.
2012-10-12 16:31:07.382 MyApp[3295:611b] Listening.
2012-10-12 16:31:07.383 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.NO DETECTION HERE
2012-10-12 16:31:42.355 MyApp[3295:174f] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_046 ———————– Stopping
2012-10-12 16:31:42.385 MyApp[3295:611b] Stopping audio unit.
2012-10-12 16:31:42.493 MyApp[3295:611b] Audio Output Unit stopped, cleaning up variable states.
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.08 CPU 0.109 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 1.66 wall 2.159 xRT
INFO: ngram_search_fwdflat.c(185): TOTAL fwdflat 0.00 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(188): TOTAL fwdflat 0.01 wall 0.008 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(323): TOTAL bestpath 0.00 wall 0.000 xRT
2012-10-12 16:31:42.497 MyApp[3295:611b] This device is not recording, so first we will set its recording status to 0
2012-10-12 16:31:42.498 MyApp[3295:611b] The audio unit is running so we are going to dispose of its instance
2012-10-12 16:31:42.500 MyApp[3295:611b] No longer listening.
2012-10-12 16:31:42.502 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStopListening] Pocketsphinx has stopped listening.
2012-10-12 16:31:42.572 MyApp[3295:174f] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_046 ———————– Stopping finished
2012-10-12 16:31:44.490 MyApp[3295:907] -[PDFPresentationView dealloc]: <PDFPresentationView: 0x20830d40; frame = (0 0; 320 568); autoresize = W+H; gestureRecognizers = ; layer = >
2012-10-12 16:31:44.492 MyApp[3295:907] -[PresentationBaseView dealloc]0
2012-10-12 16:31:44.497 MyApp[3295:907] -[PDFPresentationView dealloc]: <PDFPresentationView: 0x1f566950; frame = (0 0; 1280 720); clipsToBounds = YES; alpha = 0; autoresize = W+H; layer = >
2012-10-12 16:31:44.498 MyApp[3295:907] -[PresentationBaseView dealloc]1
2012-10-12 16:31:51.204 MyApp[3295:907] +[DocumentHelper documentTypeFromUrl:] pathExtension: pdf
2012-10-12 16:31:51.208 MyApp[3295:907] -[PresentationBaseView ensureExternalPresentationView]0 <ExternalScreenWindow: 0x1f538640; baseClass = UIWindow; frame = (0 0; 1280 720); layer = >
2012-10-12 16:31:51.217 MyApp[3295:907] -[PDFPresentationView configurePage:forIndex:]0 page index: 0, current 0
2012-10-12 16:31:51.221 MyApp[3295:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 16:31:51.271 MyApp[3295:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 16:31:51.722 MyApp[3295:1753] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting
2012-10-12 16:31:51.725 MyApp[3295:1753] Starting OpenEars logging for OpenEars version {{{{1.2.2}}}} on device: iPhone running iOS version: 6.000000
2012-10-12 16:31:51.726 MyApp[3295:1753] A sample rate was requested that isn’t one of the two supported values of 16000 or 8000 so we will use the default of 16000.
2012-10-12 16:31:51.727 MyApp[3295:1753] The audio session has already been initialized but we will override its properties.
2012-10-12 16:31:51.727 MyApp[3295:1753] Checking and resetting all audio session settings.
2012-10-12 16:31:51.729 MyApp[3295:1753] audioCategory is correct, we will leave it as it is.
2012-10-12 16:31:51.730 MyApp[3295:1753] bluetoothInput is correct, we will leave it as it is.
2012-10-12 16:31:51.730 MyApp[3295:1753] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 16:31:51.732 MyApp[3295:1753] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 16:31:51.733 MyApp[3295:1753] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 16:31:51.734 MyApp[3295:1753] AudioSessionManager startAudioSession has reached the end of the initialization.
2012-10-12 16:31:51.735 MyApp[3295:1753] Exiting startAudioSession.
2012-10-12 16:31:51.737 MyApp[3295:740b] Recognition loop has started
2012-10-12 16:31:51.737 MyApp[3295:1753] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting finished
INFO: cmd_ln.c(706): Parsing command line:
\
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel \
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic \
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app \
-lw 6.500000 \
-maxhmmpf 3000 \
-samprate 16000Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-argfile
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app
-input_endian little little
-jsgf
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latsize 5000 5000
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel
-lmctl
-lmname default default
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf -1 3000
-maxnewoov 20 20
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-5 1.000000e-05
-pl_window 0 0
-rawlogdir
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-usewdphones no no
-uw 1.0 1.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02INFO: cmd_ln.c(706): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 47 \
-varnorm noCurrent configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 47
-dither no no
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.000000e+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec 0-12/13-25/26-38
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear-wlen 0.025625 2.500000e-02
INFO: acmod.c(250): Parsed model-specific feature parameters from /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/feat.params
INFO: feat.c(713): Initializing feature stream to type: ‘1s_c_d_dd’, ceplen=13, CMN=’current’, VARNORM=’no’, AGC=’none’
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(171): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/transition_matrices
INFO: acmod.c(125): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(995): Loading senones from dump file /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/sendump
INFO: s2_semi_mgau.c(1019): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1114): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1391): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4110 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 3 words read
INFO: dict.c(341): Reading filler dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(400): Building PID tables for dictionary
INFO: dict2pid.c(408): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones
INFO: dict2pid.c(135): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(199): Allocated 30200 bytes (29 KiB) for single-phone word triphones
INFO: ngram_model_arpa.c(488): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa.c(143): Reading unigrams
INFO: ngram_model_arpa.c(528): 4 = #unigrams created
INFO: ngram_model_arpa.c(204): Reading bigrams
INFO: ngram_model_arpa.c(547): 4 = #bigrams created
INFO: ngram_model_arpa.c(548): 3 = #prob2 entries
INFO: ngram_model_arpa.c(558): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(302): Reading trigrams
INFO: ngram_model_arpa.c(573): 2 = #trigrams created
INFO: ngram_model_arpa.c(574): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 2 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 132
INFO: ngram_search_fwdtree.c(338): after: 2 root, 4 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(167): fwdflat: min_ef_width = 4, max_sf_win = 25
2012-10-12 16:31:51.845 MyApp[3295:740b] Starting openAudioDevice on the device.
2012-10-12 16:31:51.847 MyApp[3295:740b] Audio unit wrapper successfully created.
2012-10-12 16:31:51.854 MyApp[3295:740b] Set audio route to AirTunes
2012-10-12 16:31:51.855 MyApp[3295:740b] Checking and resetting all audio session settings.
2012-10-12 16:31:51.857 MyApp[3295:740b] audioCategory is correct, we will leave it as it is.
2012-10-12 16:31:51.858 MyApp[3295:740b] bluetoothInput is correct, we will leave it as it is.
2012-10-12 16:31:51.859 MyApp[3295:740b] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 16:31:51.862 MyApp[3295:740b] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 16:31:51.863 MyApp[3295:740b] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 16:31:51.864 MyApp[3295:740b] Setting the variables for the device and starting it.
2012-10-12 16:31:51.865 MyApp[3295:740b] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 16:31:57.485 MyApp[3295:740b] 16:31:57.485 AUIOClient_StartIO failed (2003329396)
2012-10-12 16:31:57.486 MyApp[3295:740b] Couldn’t start audio unit output: 2003329396
2012-10-12 16:31:57.486 MyApp[3295:740b] startRecording failed
2012-10-12 16:31:57.487 MyApp[3295:740b] Calibration has started
2012-10-12 16:31:57.487 MyApp[3295:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
2012-10-12 16:31:57.489 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStartCalibration] Pocketsphinx calibration has started.
2012-10-12 16:31:59.723 MyApp[3295:740b] cont_ad_calib failed
2012-10-12 16:31:59.725 MyApp[3295:740b] Calibration has completed
2012-10-12 16:31:59.725 MyApp[3295:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
2012-10-12 16:31:59.727 MyApp[3295:740b] Project has these words in its dictionary:
BACK
NEXT
NEXT(2)2012-10-12 16:31:59.727 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidCompleteCalibration] Pocketsphinx calibration is complete.
2012-10-12 16:31:59.729 MyApp[3295:740b] Listening.
2012-10-12 16:31:59.729 MyApp[3295:740b] cont_ad_read failed
2012-10-12 16:31:59.729 MyApp[3295:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 16:31:59.730 MyApp[3295:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
(lldb)FermParticipantCould it have to do with some output signal rerouting going on with AirPlay? Since the output probably goes to the AirPlay receiver.
I do not need output since I only use speech recognition not synthesizing.
FermParticipantThanks for the rapid answer.
Yes you right, it seems to be related to AirPlay. I been testing since I posted without airplay and I cannot reproduce.
Here’s the whole log (including some application logs).
2012-10-12 15:14:49.709 MyApp[3103:1603] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting
2012-10-12 15:14:49.792 MyApp[3103:6403] Recognition loop has started
INFO: cmd_ln.c(706): Parsing command line:
\
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel \
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic \
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app \
-lw 6.500000 \
-maxhmmpf 3000
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-argfile
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app
-input_endian little little
-jsgf
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latsize 5000 5000
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel
-lmctl
-lmname default default
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf -1 3000
-maxnewoov 20 20
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-5 1.000000e-05
-pl_window 0 0
-rawlogdir
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-usewdphones no no
-uw 1.0 1.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02
2012-10-12 15:14:49.804 MyApp[3103:1603] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting finished
INFO: cmd_ln.c(706): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 47 \
-varnorm no
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 47
-dither no no
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.000000e+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec 0-12/13-25/26-38
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(250): Parsed model-specific feature parameters from /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/feat.params
INFO: feat.c(713): Initializing feature stream to type: ‘1s_c_d_dd’, ceplen=13, CMN=’current’, VARNORM=’no’, AGC=’none’
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(171): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/transition_matrices
INFO: acmod.c(125): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(995): Loading senones from dump file /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/sendump
INFO: s2_semi_mgau.c(1019): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1114): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1391): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4110 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 3 words read
INFO: dict.c(341): Reading filler dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(400): Building PID tables for dictionary
INFO: dict2pid.c(408): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones
INFO: dict2pid.c(135): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(199): Allocated 30200 bytes (29 KiB) for single-phone word triphones
INFO: ngram_model_arpa.c(488): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa.c(143): Reading unigrams
INFO: ngram_model_arpa.c(528): 4 = #unigrams created
INFO: ngram_model_arpa.c(204): Reading bigrams
INFO: ngram_model_arpa.c(547): 4 = #bigrams created
INFO: ngram_model_arpa.c(548): 3 = #prob2 entries
INFO: ngram_model_arpa.c(558): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(302): Reading trigrams
INFO: ngram_model_arpa.c(573): 2 = #trigrams created
INFO: ngram_model_arpa.c(574): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 2 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 132
INFO: ngram_search_fwdtree.c(338): after: 2 root, 4 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(167): fwdflat: min_ef_width = 4, max_sf_win = 25
2012-10-12 15:14:49.934 MyApp[3103:6403] Starting openAudioDevice on the device.
2012-10-12 15:14:49.936 MyApp[3103:6403] Audio unit wrapper successfully created.
2012-10-12 15:14:49.942 MyApp[3103:6403] Set audio route to SpeakerAndMicrophone
2012-10-12 15:14:49.943 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:14:49.946 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:14:49.947 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:14:49.948 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:14:49.950 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:14:49.952 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:14:49.953 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:14:49.956 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:14:50.453 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:14:50.457 MyApp[3103:6403] Calibration has started
2012-10-12 15:14:50.457 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartCalibration] Pocketsphinx calibration has started.
2012-10-12 15:14:52.694 MyApp[3103:6403] Calibration has completed
2012-10-12 15:14:52.694 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidCompleteCalibration] Pocketsphinx calibration is complete.
2012-10-12 15:14:52.698 MyApp[3103:6403] Project has these words in its dictionary:
BACK
NEXT
NEXT(2)
2012-10-12 15:14:52.701 MyApp[3103:6403] Listening.
2012-10-12 15:14:52.702 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:14:55.044 MyApp[3103:6403] Speech detected…
2012-10-12 15:14:55.047 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:14:56.214 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:14:56.215 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:14:56.346 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:14:56.347 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 601 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 5706 senones evaluated (98/fr)
INFO: ngram_search_fwdtree.c(1553): 3141 channels searched (54/fr), 108 1st, 2850 last
INFO: ngram_search_fwdtree.c(1557): 691 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 89 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.109 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.36 wall 2.340 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 163 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 5573 senones evaluated (96/fr)
INFO: ngram_search_fwdflat.c(955): 3705 channels searched (63/fr)
INFO: ngram_search_fwdflat.c(957): 312 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 177 word transitions (3/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.008 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .45
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 17 nodes, 23 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:45:56) = -385635
INFO: ps_lattice.c(1405): Joint P(O,S) = -391118 P(S|O) = -5483
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:14:56.356 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-5483) and an utterance ID of 000000000.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6288)
2012-10-12 15:14:56.358 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:14:56.358 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6288”;
}
)
2012-10-12 15:14:56.361 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:14:56.362 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:14:56.364 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:14:56.365 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:14:56.367 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:14:56.368 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:14:56.370 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:14:56.469 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:14:56.473 MyApp[3103:6403] Listening.
2012-10-12 15:14:56.473 MyApp[3103:150b] -[PDFPresentationView configurePage:forIndex:]0 page index: 1, current 1
2012-10-12 15:14:56.479 MyApp[3103:150b] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:14:56.481 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:14:58.432 MyApp[3103:6403] Speech detected…
2012-10-12 15:14:58.433 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:14:59.542 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:14:59.542 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:14:59.670 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:14:59.672 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 633 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 5825 senones evaluated (100/fr)
INFO: ngram_search_fwdtree.c(1553): 3184 channels searched (54/fr), 108 1st, 2887 last
INFO: ngram_search_fwdtree.c(1557): 690 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 103 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.081 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.25 wall 2.160 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 162 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 5887 senones evaluated (101/fr)
INFO: ngram_search_fwdflat.c(955): 3942 channels searched (67/fr)
INFO: ngram_search_fwdflat.c(957): 304 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 160 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.014 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.011 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .43
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 14 nodes, 19 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:43:56) = -379780
INFO: ps_lattice.c(1405): Joint P(O,S) = -388917 P(S|O) = -9137
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:14:59.681 MyApp[3103:6403] Pocketsphinx heard “BACK” with a score of (-9137) and an utterance ID of 000000001.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-6157)
2012-10-12 15:14:59.682 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:14:59.682 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-6157”;
}
)
2012-10-12 15:14:59.683 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:14:59.684 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:14:59.685 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:14:59.686 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:14:59.687 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:14:59.687 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:14:59.688 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:14:59.797 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:14:59.798 MyApp[3103:6403] Listening.
2012-10-12 15:14:59.800 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:01.643 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:01.644 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:02.869 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:02.870 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:02.998 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:03.000 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 669 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 6834 senones evaluated (110/fr)
INFO: ngram_search_fwdtree.c(1553): 3852 channels searched (62/fr), 116 1st, 3527 last
INFO: ngram_search_fwdtree.c(1557): 737 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 114 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.074 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.37 wall 2.205 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 188 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 6409 senones evaluated (103/fr)
INFO: ngram_search_fwdflat.c(955): 4268 channels searched (68/fr)
INFO: ngram_search_fwdflat.c(957): 324 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 157 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.013 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.011 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .47
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 11 nodes, 14 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:47:60) = -422761
INFO: ps_lattice.c(1405): Joint P(O,S) = -432539 P(S|O) = -9778
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:03.009 MyApp[3103:6403] Pocketsphinx heard “BACK” with a score of (-9778) and an utterance ID of 000000002.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-6754)
2012-10-12 15:15:03.010 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:03.010 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-6754”;
}
)
2012-10-12 15:15:03.012 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:03.013 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:03.013 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:03.014 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:03.015 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:03.016 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:03.017 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:03.125 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:03.127 MyApp[3103:6403] Listening.
2012-10-12 15:15:03.128 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:05.479 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:05.480 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:06.842 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:06.842 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:06.966 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:06.968 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 751 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 6937 senones evaluated (105/fr)
INFO: ngram_search_fwdtree.c(1553): 3874 channels searched (58/fr), 124 1st, 3539 last
INFO: ngram_search_fwdtree.c(1557): 801 words for which last channels evaluated (12/fr)
INFO: ngram_search_fwdtree.c(1560): 117 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.079 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.50 wall 2.270 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 208 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 6423 senones evaluated (97/fr)
INFO: ngram_search_fwdflat.c(955): 4259 channels searched (64/fr)
INFO: ngram_search_fwdflat.c(957): 349 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 180 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .48
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 14 nodes, 20 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:48:64) = -429193
INFO: ps_lattice.c(1405): Joint P(O,S) = -436788 P(S|O) = -7595
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:06.977 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-7595) and an utterance ID of 000000003.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6661)
2012-10-12 15:15:06.978 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:06.978 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6661”;
}
)
2012-10-12 15:15:06.980 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:06.980 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:06.981 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:06.982 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:06.983 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:06.984 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:06.985 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:07.093 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:07.094 MyApp[3103:6403] Listening.
2012-10-12 15:15:07.096 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:13.048 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:13.049 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:16.311 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:16.311 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:16.438 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:16.440 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 2160 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 15202 senones evaluated (68/fr)
INFO: ngram_search_fwdtree.c(1553): 6398 channels searched (28/fr), 440 1st, 5271 last
INFO: ngram_search_fwdtree.c(1557): 2368 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 247 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.20 CPU 0.091 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 3.40 wall 1.518 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 691 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 16241 senones evaluated (73/fr)
INFO: ngram_search_fwdflat.c(955): 9549 channels searched (42/fr)
INFO: ngram_search_fwdflat.c(957): 977 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 197 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.02 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.02 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .195
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 27 nodes, 21 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:195:222) = -1472131
INFO: ps_lattice.c(1405): Joint P(O,S) = -1478401 P(S|O) = -6270
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:16.464 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-6270) and an utterance ID of 000000004.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-25576)
2012-10-12 15:15:16.465 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:16.465 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-25576”;
}
)
2012-10-12 15:15:16.467 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:16.468 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:16.469 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:16.470 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:16.471 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:16.471 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:16.472 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:16.565 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:16.566 MyApp[3103:6403] Listening.
2012-10-12 15:15:16.568 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:17.093 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:17.094 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:18.357 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:18.358 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:18.486 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:18.488 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 563 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 3401 senones evaluated (59/fr)
INFO: ngram_search_fwdtree.c(1553): 1298 channels searched (22/fr), 108 1st, 1005 last
INFO: ngram_search_fwdtree.c(1557): 607 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 79 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.04 CPU 0.077 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.40 wall 2.421 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(951): 108 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 171 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(955): 162 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(957): 162 words searched (2/fr)
INFO: ngram_search_fwdflat.c(959): 63 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.00 wall 0.007 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .37
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 20 nodes, 5 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:37:56) = -423180
INFO: ps_lattice.c(1405): Joint P(O,S) = -423303 P(S|O) = -123
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:18.494 MyApp[3103:6403] Pocketsphinx heard “” with a score of (-123) and an utterance ID of 000000005.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: (null) (-6250)
2012-10-12 15:15:18.496 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:18.496 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = “(null)”;
Score = “-6250”;
}
)
2012-10-12 15:15:18.497 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:18.498 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:18.499 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:18.500 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:18.501 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:18.502 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:18.502 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:18.613 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:18.614 MyApp[3103:6403] Listening.
2012-10-12 15:15:18.616 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:37.985 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:37.986 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:39.607 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:39.607 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:39.736 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:39.737 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 977 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 8459 senones evaluated (85/fr)
INFO: ngram_search_fwdtree.c(1553): 4208 channels searched (42/fr), 189 1st, 3680 last
INFO: ngram_search_fwdtree.c(1557): 1077 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 135 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.071 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.76 wall 1.778 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 210 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 10023 senones evaluated (101/fr)
INFO: ngram_search_fwdflat.c(955): 6576 channels searched (66/fr)
INFO: ngram_search_fwdflat.c(957): 441 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 166 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.010 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1217): not found in last frame, using .97 instead
INFO: ngram_search.c(1269): lattice start node .0 end node .63
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 25 nodes, 19 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:63:97) = -699783
INFO: ps_lattice.c(1405): Joint P(O,S) = -703643 P(S|O) = -3860
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:39.749 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-3860) and an utterance ID of 000000006.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-9364)
2012-10-12 15:15:39.750 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:39.751 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:39.752 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:39.753 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:39.754 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:39.755 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:39.756 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:39.756 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:39.758 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-9364”;
}
)
2012-10-12 15:15:39.861 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:39.863 MyApp[3103:6403] Listening.
2012-10-12 15:15:39.864 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:39.869 MyApp[3103:5b43] -[PDFPresentationView configurePage:forIndex:]0 page index: 2, current 2
2012-10-12 15:15:39.873 MyApp[3103:5b43] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:15:41.440 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:41.441 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:42.808 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:42.811 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:42.934 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:42.936 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 738 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 6299 senones evaluated (82/fr)
INFO: ngram_search_fwdtree.c(1553): 3134 channels searched (40/fr), 140 1st, 2750 last
INFO: ngram_search_fwdtree.c(1557): 824 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 101 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.12 CPU 0.157 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.50 wall 1.954 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 170 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 7426 senones evaluated (96/fr)
INFO: ngram_search_fwdflat.c(955): 4924 channels searched (63/fr)
INFO: ngram_search_fwdflat.c(957): 386 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 207 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .58
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 22 nodes, 21 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:58:75) = -488258
INFO: ps_lattice.c(1405): Joint P(O,S) = -494952 P(S|O) = -6694
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:42.946 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-6694) and an utterance ID of 000000007.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-7327)
2012-10-12 15:15:42.947 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:42.949 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:42.950 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:42.951 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:42.952 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:42.952 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:42.953 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:42.954 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:42.955 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-7327”;
}
)
2012-10-12 15:15:43.061 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:43.063 MyApp[3103:6403] Listening.
2012-10-12 15:15:43.064 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:50.647 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:50.648 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:52.152 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:52.153 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:52.278 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:52.280 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 945 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 8040 senones evaluated (84/fr)
INFO: ngram_search_fwdtree.c(1553): 3995 channels searched (41/fr), 184 1st, 3500 last
INFO: ngram_search_fwdtree.c(1557): 1075 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 115 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.064 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.64 wall 1.710 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 222 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 6019 senones evaluated (63/fr)
INFO: ngram_search_fwdflat.c(955): 3759 channels searched (39/fr)
INFO: ngram_search_fwdflat.c(957): 375 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 164 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.009 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .81
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 32 nodes, 16 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:81:94) = -604925
INFO: ps_lattice.c(1405): Joint P(O,S) = -609230 P(S|O) = -4305
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:52.291 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-4305) and an utterance ID of 000000008.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-10424)
2012-10-12 15:15:52.292 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:52.292 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-10424”;
}
)
2012-10-12 15:15:52.294 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:52.295 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:52.296 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:52.297 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:52.298 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:52.298 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:52.299 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:52.405 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:52.407 MyApp[3103:6403] Listening.
2012-10-12 15:15:52.408 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:54.378 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:54.379 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:55.864 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:55.864 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:55.990 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:55.992 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 897 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 7384 senones evaluated (87/fr)
INFO: ngram_search_fwdtree.c(1553): 3671 channels searched (43/fr), 162 1st, 3231 last
INFO: ngram_search_fwdtree.c(1557): 982 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 124 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.072 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.62 wall 1.909 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 248 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 8320 senones evaluated (98/fr)
INFO: ngram_search_fwdflat.c(955): 5496 channels searched (64/fr)
INFO: ngram_search_fwdflat.c(957): 422 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 205 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.009 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .52
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 25 nodes, 44 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:52:83) = -525262
INFO: ps_lattice.c(1405): Joint P(O,S) = -532584 P(S|O) = -7322
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:56.002 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-7322) and an utterance ID of 000000009.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6631)
2012-10-12 15:15:56.003 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:56.003 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6631”;
}
)
2012-10-12 15:15:56.005 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:56.006 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:56.007 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:56.008 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:56.009 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:56.010 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:56.010 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:56.117 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:56.119 MyApp[3103:6403] Listening.
2012-10-12 15:15:56.120 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:15:58.087 MyApp[3103:6403] Speech detected…
2012-10-12 15:15:58.088 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:15:59.445 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:15:59.446 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:15:59.575 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:15:59.576 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 798 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 6888 senones evaluated (88/fr)
INFO: ngram_search_fwdtree.c(1553): 3543 channels searched (45/fr), 148 1st, 3146 last
INFO: ngram_search_fwdtree.c(1557): 879 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 116 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.068 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.50 wall 1.919 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 181 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 5222 senones evaluated (67/fr)
INFO: ngram_search_fwdflat.c(955): 3287 channels searched (42/fr)
INFO: ngram_search_fwdflat.c(957): 319 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 157 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .61
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 22 nodes, 21 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:61:76) = -500577
INFO: ps_lattice.c(1405): Joint P(O,S) = -507701 P(S|O) = -7124
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:15:59.585 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-7124) and an utterance ID of 000000010.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-7972)
2012-10-12 15:15:59.586 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:15:59.586 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-7972”;
}
)
2012-10-12 15:15:59.588 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:15:59.589 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:15:59.590 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:15:59.591 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:15:59.592 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:15:59.592 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:15:59.593 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:15:59.701 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:15:59.703 MyApp[3103:6403] Listening.
2012-10-12 15:15:59.704 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:01.171 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:01.172 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:02.648 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:02.648 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:02.776 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:02.777 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 781 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 6677 senones evaluated (86/fr)
INFO: ngram_search_fwdtree.c(1553): 3346 channels searched (42/fr), 148 1st, 2948 last
INFO: ngram_search_fwdtree.c(1557): 875 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 119 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.073 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.61 wall 2.069 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 182 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 5321 senones evaluated (68/fr)
INFO: ngram_search_fwdflat.c(955): 3350 channels searched (42/fr)
INFO: ngram_search_fwdflat.c(957): 319 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 157 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.009 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .46
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 19 nodes, 19 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:46:76) = -502379
INFO: ps_lattice.c(1405): Joint P(O,S) = -504679 P(S|O) = -2300
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:02.786 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-2300) and an utterance ID of 000000011.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-5936)
2012-10-12 15:16:02.787 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:02.788 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-5936”;
}
)
2012-10-12 15:16:02.789 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:02.789 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:02.790 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:02.791 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:02.792 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:02.793 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:02.794 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:02.901 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:02.902 MyApp[3103:6403] Listening.
2012-10-12 15:16:02.904 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:02.906 MyApp[3103:6fef] -[PDFPresentationView configurePage:forIndex:]0 page index: 3, current 3
2012-10-12 15:16:02.909 MyApp[3103:6fef] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:16:04.711 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:04.712 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:05.976 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:05.977 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:06.102 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:06.104 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 730 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 6923 senones evaluated (103/fr)
INFO: ngram_search_fwdtree.c(1553): 3758 channels searched (56/fr), 126 1st, 3408 last
INFO: ngram_search_fwdtree.c(1557): 790 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 126 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.04 CPU 0.067 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.40 wall 2.093 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 212 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 6988 senones evaluated (104/fr)
INFO: ngram_search_fwdflat.c(955): 4657 channels searched (69/fr)
INFO: ngram_search_fwdflat.c(957): 345 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 164 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .45
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 11 nodes, 16 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:45:65) = -459450
INFO: ps_lattice.c(1405): Joint P(O,S) = -467355 P(S|O) = -7905
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:06.113 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-7905) and an utterance ID of 000000012.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6571)
2012-10-12 15:16:06.115 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:06.115 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6571”;
}
)
2012-10-12 15:16:06.116 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:06.117 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:06.118 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:06.119 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:06.120 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:06.121 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:06.121 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:06.128 MyApp[3103:4e2f] -[PDFPresentationView configurePage:forIndex:]0 page index: 4, current 4
2012-10-12 15:16:06.132 MyApp[3103:4e2f] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:16:06.229 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:06.230 MyApp[3103:6403] Listening.
2012-10-12 15:16:06.231 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:07.815 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:07.815 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:09.434 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:09.434 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:09.559 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:09.560 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 1133 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 8349 senones evaluated (78/fr)
INFO: ngram_search_fwdtree.c(1553): 3872 channels searched (36/fr), 206 1st, 3329 last
INFO: ngram_search_fwdtree.c(1557): 1213 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 127 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.063 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.75 wall 1.639 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 289 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 9957 senones evaluated (93/fr)
INFO: ngram_search_fwdflat.c(955): 6460 channels searched (60/fr)
INFO: ngram_search_fwdflat.c(957): 504 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 236 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.008 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .86
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 41 nodes, 32 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:86:105) = -627572
INFO: ps_lattice.c(1405): Joint P(O,S) = -627764 P(S|O) = -192
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:09.573 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-192) and an utterance ID of 000000013.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-10345)
2012-10-12 15:16:09.574 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:09.574 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-10345”;
}
)
2012-10-12 15:16:09.575 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:09.576 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:09.577 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:09.578 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:09.579 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:09.579 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:09.580 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:09.685 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:09.687 MyApp[3103:6403] Listening.
2012-10-12 15:16:09.688 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:12.298 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:12.299 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:13.654 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:13.654 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:13.782 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:13.784 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 622 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 4228 senones evaluated (64/fr)
INFO: ngram_search_fwdtree.c(1553): 1718 channels searched (26/fr), 124 1st, 1377 last
INFO: ngram_search_fwdtree.c(1557): 687 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 108 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.077 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.49 wall 2.265 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(951): 114 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 2442 senones evaluated (37/fr)
INFO: ngram_search_fwdflat.c(955): 1337 channels searched (20/fr)
INFO: ngram_search_fwdflat.c(957): 182 words searched (2/fr)
INFO: ngram_search_fwdflat.c(959): 76 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.008 xRT
INFO: ngram_search.c(1217): not found in last frame, using BACK.64 instead
INFO: ngram_search.c(1269): lattice start node .0 end node BACK.19
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 5 nodes, 2 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(BACK:19:64) = -492888
INFO: ps_lattice.c(1405): Joint P(O,S) = -492888 P(S|O) = 0
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:13.792 MyApp[3103:6403] Pocketsphinx heard “BACK” with a score of (0) and an utterance ID of 000000014.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-2927)
2012-10-12 15:16:13.793 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:13.793 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-2927”;
}
)
2012-10-12 15:16:13.794 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:13.795 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:13.796 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:13.797 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:13.798 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:13.798 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:13.799 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:13.909 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:13.910 MyApp[3103:6403] Listening.
2012-10-12 15:16:13.912 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:15.874 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:15.875 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:17.498 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:17.498 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:17.623 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:17.624 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 956 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 8347 senones evaluated (90/fr)
INFO: ngram_search_fwdtree.c(1553): 4246 channels searched (45/fr), 178 1st, 3763 last
INFO: ngram_search_fwdtree.c(1557): 1047 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 134 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.067 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.76 wall 1.892 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 212 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 9582 senones evaluated (103/fr)
INFO: ngram_search_fwdflat.c(955): 6290 channels searched (67/fr)
INFO: ngram_search_fwdflat.c(957): 417 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 200 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.001 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1217): not found in last frame, using .91 instead
INFO: ngram_search.c(1269): lattice start node .0 end node .75
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 22 nodes, 28 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:75:91) = -632531
INFO: ps_lattice.c(1405): Joint P(O,S) = -635752 P(S|O) = -3221
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:17.636 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-3221) and an utterance ID of 000000015.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-10422)
2012-10-12 15:16:17.637 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:17.637 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-10422”;
}
)
2012-10-12 15:16:17.638 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:17.639 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:17.640 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:17.641 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:17.642 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:17.643 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:17.644 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:17.749 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:17.750 MyApp[3103:6403] Listening.
2012-10-12 15:16:17.752 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:20.739 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:20.740 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:21.974 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:21.974 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:22.103 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:22.104 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 576 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 3935 senones evaluated (63/fr)
INFO: ngram_search_fwdtree.c(1553): 1608 channels searched (25/fr), 116 1st, 1286 last
INFO: ngram_search_fwdtree.c(1557): 634 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 105 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.04 CPU 0.072 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.37 wall 2.216 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(951): 102 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 183 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(955): 167 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(957): 167 words searched (2/fr)
INFO: ngram_search_fwdflat.c(959): 66 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.006 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.00 wall 0.007 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .37
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 6 nodes, 2 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:37:60) = -494010
INFO: ps_lattice.c(1405): Joint P(O,S) = -494010 P(S|O) = 0
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:22.111 MyApp[3103:6403] Pocketsphinx heard “” with a score of (0) and an utterance ID of 000000016.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: (null) (-6733)
2012-10-12 15:16:22.112 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:22.112 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = “(null)”;
Score = “-6733”;
}
)
2012-10-12 15:16:22.113 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:22.114 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:22.115 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:22.116 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:22.117 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:22.117 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:22.118 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:22.229 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:22.230 MyApp[3103:6403] Listening.
2012-10-12 15:16:22.232 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:24.315 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:24.316 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:25.686 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:25.686 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:25.814 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:25.816 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 743 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 5263 senones evaluated (71/fr)
INFO: ngram_search_fwdtree.c(1553): 2316 channels searched (31/fr), 140 1st, 1931 last
INFO: ngram_search_fwdtree.c(1557): 808 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 107 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.071 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.51 wall 2.041 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 232 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 7648 senones evaluated (103/fr)
INFO: ngram_search_fwdflat.c(955): 5093 channels searched (68/fr)
INFO: ngram_search_fwdflat.c(957): 372 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 170 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.011 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .60
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 13 nodes, 21 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:60:72) = -499380
INFO: ps_lattice.c(1405): Joint P(O,S) = -504629 P(S|O) = -5249
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:25.826 MyApp[3103:6403] Pocketsphinx heard “NEXT” with a score of (-5249) and an utterance ID of 000000017.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-8250)
2012-10-12 15:16:25.827 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:25.827 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-8250”;
}
)
2012-10-12 15:16:25.828 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:25.829 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:25.830 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:25.831 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:25.832 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:25.833 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:25.834 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:25.941 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:25.942 MyApp[3103:6403] Listening.
2012-10-12 15:16:25.944 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:38.155 MyApp[3103:6403] Speech detected…
2012-10-12 15:16:38.155 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:39.511 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:39.511 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:39.639 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:39.640 MyApp[3103:6403] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 658 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 3633 senones evaluated (52/fr)
INFO: ngram_search_fwdtree.c(1553): 1237 channels searched (17/fr), 132 1st, 909 last
INFO: ngram_search_fwdtree.c(1557): 723 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 53 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.071 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.49 wall 2.135 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 3 words
INFO: ngram_search_fwdflat.c(951): 135 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 3052 senones evaluated (44/fr)
INFO: ngram_search_fwdflat.c(955): 1702 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 235 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 105 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.005 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .37
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 22 nodes, 2 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:37:68) = -420282
INFO: ps_lattice.c(1405): Joint P(O,S) = -420282 P(S|O) = 0
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:39.648 MyApp[3103:6403] Pocketsphinx heard “” with a score of (0) and an utterance ID of 000000018.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: (null) (-4445)
2012-10-12 15:16:39.650 MyApp[3103:6403] Checking and resetting all audio session settings.
2012-10-12 15:16:39.650 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = “(null)”;
Score = “-4445”;
}
)
2012-10-12 15:16:39.651 MyApp[3103:6403] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:39.652 MyApp[3103:6403] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:39.653 MyApp[3103:6403] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:39.654 MyApp[3103:6403] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:39.655 MyApp[3103:6403] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:39.656 MyApp[3103:6403] Setting the variables for the device and starting it.
2012-10-12 15:16:39.656 MyApp[3103:6403] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:39.765 MyApp[3103:6403] Started audio output unit.
2012-10-12 15:16:39.766 MyApp[3103:6403] Listening.
2012-10-12 15:16:39.768 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:50.121 MyApp[3103:907] -[MyAppAppDelegate applicationDidBecomeActive:] Num screens 1
2012-10-12 15:16:50.888 MyApp[3103:907] Audio route has changed for the following reason:
2012-10-12 15:16:50.889 MyApp[3103:907] A new device has become available
2012-10-12 15:16:50.890 MyApp[3103:907] The previous audio route was SpeakerAndMicrophone
2012-10-12 15:16:50.891 MyApp[3103:907] This is a case for performing a route change. Before the route change, the current route is AirTunes
2012-10-12 15:16:50.891 MyApp[3103:907] Performing Audio Route change.
2012-10-12 15:16:50.892 MyApp[3103:907] The new audio route is AirTunes
2012-10-12 15:16:50.893 MyApp[3103:907] -[SpeechRecognizer audioRouteDidChangeToRoute:] Audio route change. The new audio route is AirTunes
2012-10-12 15:16:50.927 MyApp[3103:6403] Stopping audio unit.
2012-10-12 15:16:50.996 MyApp[3103:6403] Audio Output Unit stopped, cleaning up variable states.
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 1.25 CPU 0.080 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 30.71 wall 1.970 xRT
INFO: ngram_search_fwdflat.c(185): TOTAL fwdflat 0.12 CPU 0.008 xRT
INFO: ngram_search_fwdflat.c(188): TOTAL fwdflat 0.15 wall 0.010 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(323): TOTAL bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:51.000 MyApp[3103:6403] This device is not recording, so first we will set its recording status to 0
2012-10-12 15:16:51.001 MyApp[3103:6403] The audio unit is running so we are going to dispose of its instance
2012-10-12 15:16:51.002 MyApp[3103:6403] No longer listening.
2012-10-12 15:16:51.006 MyApp[3103:6407] Recognition loop has started
INFO: cmd_ln.c(706): Parsing command line:
\
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel \
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic \
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app \
-lw 6.500000 \
-maxhmmpf 3000
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-argfile
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app
-input_endian little little
-jsgf
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latsize 5000 5000
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel
-lmctl
-lmname default default
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf -1 3000
-maxnewoov 20 20
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-5 1.000000e-05
-pl_window 0 0
-rawlogdir
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 2012-10-12 15:16:51.015 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStopListening] Pocketsphinx has stopped listening.
0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-usewdphones no no
-uw 1.0 1.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
2012-10-12 15:16:51.016 MyApp[3103:907] -[SpeechRecognizer pocketsphinxRecognitionLoopDidStart-warp_type ] Pocketsphinx is starting up.
inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02
INFO: cmd_ln.c(706): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 47 \
-varnorm no
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 47
-dither no no
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.000000e+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec 0-12/13-25/26-38
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(250): Parsed model-specific feature parameters from /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/feat.params
INFO: feat.c(713): Initializing feature stream to type: ‘1s_c_d_dd’, ceplen=13, CMN=’current’, VARNORM=’no’, AGC=’none’
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(171): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/transition_matrices
INFO: acmod.c(125): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(995): Loading senones from dump file /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/sendump
INFO: s2_semi_mgau.c(1019): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1114): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1391): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4110 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 3 words read
INFO: dict.c(341): Reading filler dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(400): Building PID tables for dictionary
INFO: dict2pid.c(408): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones
INFO: dict2pid.c(135): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(199): Allocated 30200 bytes (29 KiB) for single-phone word triphones
INFO: ngram_model_arpa.c(488): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa.c(143): Reading unigrams
INFO: ngram_model_arpa.c(528): 4 = #unigrams created
INFO: ngram_model_arpa.c(204): Reading bigrams
INFO: ngram_model_arpa.c(547): 4 = #bigrams created
INFO: ngram_model_arpa.c(548): 3 = #prob2 entries
INFO: ngram_model_arpa.c(558): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(302): Reading trigrams
INFO: ngram_model_arpa.c(573): 2 = #trigrams created
INFO: ngram_model_arpa.c(574): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 2 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 132
INFO: ngram_search_fwdtree.c(338): after: 2 root, 4 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(167): fwdflat: min_ef_width = 4, max_sf_win = 25
2012-10-12 15:16:51.129 MyApp[3103:6407] Starting openAudioDevice on the device.
2012-10-12 15:16:51.129 MyApp[3103:6407] Audio unit wrapper successfully created.
2012-10-12 15:16:51.137 MyApp[3103:6407] Set audio route to AirTunes
2012-10-12 15:16:51.137 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:16:51.138 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:51.139 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:51.140 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:51.141 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:51.142 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:51.143 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:16:51.144 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:51.274 MyApp[3103:6017] Audio Unit render error -1: unknown error
2012-10-12 15:16:51.277 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:16:51.278 MyApp[3103:6407] Calibration has started
2012-10-12 15:16:51.279 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartCalibration] Pocketsphinx calibration has started.
2012-10-12 15:16:51.280 MyApp[3103:907] -[MyAppAppDelegate screenDidConnect:] <UIScreen: 0x2103ebf0; bounds = {{0, 0}, {1280, 720}}; mode = >
2012-10-12 15:16:51.355 MyApp[3103:907] -[PresentationBaseView externalScreenDidConnect:] <ExternalScreenWindow: 0x1fd60920; baseClass = UIWindow; frame = (0 0; 1280 720); layer = >
2012-10-12 15:16:51.356 MyApp[3103:907] -[PresentationBaseView ensureExternalPresentationView]0 <ExternalScreenWindow: 0x1fd60920; baseClass = UIWindow; frame = (0 0; 1280 720); layer = >
2012-10-12 15:16:51.360 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:16:53.518 MyApp[3103:6407] Calibration has completed
2012-10-12 15:16:53.519 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidCompleteCalibration] Pocketsphinx calibration is complete.
2012-10-12 15:16:53.522 MyApp[3103:6407] Project has these words in its dictionary:
BACK
NEXT
NEXT(2)
2012-10-12 15:16:53.523 MyApp[3103:6407] Listening.
2012-10-12 15:16:53.523 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:58.075 MyApp[3103:6407] Speech detected…
2012-10-12 15:16:58.076 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:16:59.172 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:16:59.176 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:16:59.262 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:16:59.264 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 535 words recognized (9/fr)
INFO: ngram_search_fwdtree.c(1551): 3928 senones evaluated (68/fr)
INFO: ngram_search_fwdtree.c(1553): 1751 channels searched (30/fr), 108 1st, 1458 last
INFO: ngram_search_fwdtree.c(1557): 615 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 97 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.05 CPU 0.089 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.20 wall 2.069 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 3 words
INFO: ngram_search_fwdflat.c(951): 119 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 2623 senones evaluated (45/fr)
INFO: ngram_search_fwdflat.c(955): 1409 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 207 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 97 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .36
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 9 nodes, 7 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:36:56) = -438136
INFO: ps_lattice.c(1405): Joint P(O,S) = -438581 P(S|O) = -445
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:16:59.271 MyApp[3103:6407] Pocketsphinx heard “NEXT” with a score of (-445) and an utterance ID of 000000000.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-5745)
2012-10-12 15:16:59.273 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:16:59.275 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:16:59.276 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:16:59.278 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:16:59.275 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-5745”;
}
)
2012-10-12 15:16:59.281 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:16:59.283 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:16:59.284 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:16:59.285 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:16:59.353 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:16:59.355 MyApp[3103:6407] Listening.
2012-10-12 15:16:59.357 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:16:59.361 MyApp[3103:5b37] -[PDFPresentationView configurePage:forIndex:]0 page index: 5, current 5
2012-10-12 15:16:59.366 MyApp[3103:5b37] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:16:59.602 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:03.404 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:03.405 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:04.744 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:04.746 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:04.835 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:04.836 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 697 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 5057 senones evaluated (72/fr)
INFO: ngram_search_fwdtree.c(1553): 2331 channels searched (33/fr), 132 1st, 1979 last
INFO: ngram_search_fwdtree.c(1557): 763 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 97 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.089 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.44 wall 2.060 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 3 words
INFO: ngram_search_fwdflat.c(951): 157 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 3049 senones evaluated (44/fr)
INFO: ngram_search_fwdflat.c(955): 1706 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 242 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 124 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.008 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .48
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 25 nodes, 14 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:48:68) = -458218
INFO: ps_lattice.c(1405): Joint P(O,S) = -458446 P(S|O) = -228
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.001 xRT
2012-10-12 15:17:04.847 MyApp[3103:6407] Pocketsphinx heard “BACK” with a score of (-228) and an utterance ID of 000000001.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-6626)
2012-10-12 15:17:04.848 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:04.849 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-6626”;
}
)
2012-10-12 15:17:04.850 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:04.851 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:04.852 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:04.854 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:04.855 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:04.855 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:04.856 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:04.927 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:04.928 MyApp[3103:6407] Listening.
2012-10-12 15:17:04.929 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:05.167 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:13.772 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:13.773 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:15.144 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:15.145 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:15.239 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:15.240 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 757 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 5409 senones evaluated (72/fr)
INFO: ngram_search_fwdtree.c(1553): 2480 channels searched (33/fr), 142 1st, 2114 last
INFO: ngram_search_fwdtree.c(1557): 816 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 91 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.080 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.48 wall 1.969 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 162 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 5334 senones evaluated (71/fr)
INFO: ngram_search_fwdflat.c(955): 3189 channels searched (42/fr)
INFO: ngram_search_fwdflat.c(957): 313 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 154 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.007 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.009 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .46
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 15 nodes, 17 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:46:73) = -467647
INFO: ps_lattice.c(1405): Joint P(O,S) = -470119 P(S|O) = -2472
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:15.249 MyApp[3103:6407] Pocketsphinx heard “NEXT” with a score of (-2472) and an utterance ID of 000000002.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6196)
2012-10-12 15:17:15.250 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:15.250 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6196”;
}
)
2012-10-12 15:17:15.252 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:15.253 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:15.253 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:15.254 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:15.255 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:15.256 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:15.257 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:15.329 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:15.331 MyApp[3103:6407] Listening.
2012-10-12 15:17:15.333 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:15.566 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:18.712 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:18.713 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:20.252 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:20.253 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:20.346 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:20.347 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 652 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551): 5124 senones evaluated (64/fr)
INFO: ngram_search_fwdtree.c(1553): 2159 channels searched (26/fr), 152 1st, 1811 last
INFO: ngram_search_fwdtree.c(1557): 847 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 49 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.083 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.64 wall 2.053 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 3 words
INFO: ngram_search_fwdflat.c(951): 144 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 3502 senones evaluated (44/fr)
INFO: ngram_search_fwdflat.c(955): 1946 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 259 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 120 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.003 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.008 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .58
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 21 nodes, 20 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:58:78) = -473353
INFO: ps_lattice.c(1405): Joint P(O,S) = -473602 P(S|O) = -249
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:20.356 MyApp[3103:6407] Pocketsphinx heard “BACK” with a score of (-249) and an utterance ID of 000000003.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-6713)
2012-10-12 15:17:20.357 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:20.359 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:20.360 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:20.357 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-6713”;
}
)
2012-10-12 15:17:20.362 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:20.364 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:20.365 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:20.366 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:20.366 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:20.437 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:20.439 MyApp[3103:6407] Listening.
2012-10-12 15:17:20.440 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:20.685 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:22.434 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:22.435 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:23.969 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:23.969 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:24.061 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:24.062 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 753 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 5408 senones evaluated (73/fr)
INFO: ngram_search_fwdtree.c(1553): 2510 channels searched (33/fr), 140 1st, 2137 last
INFO: ngram_search_fwdtree.c(1557): 805 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 96 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.06 CPU 0.087 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.64 wall 2.212 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 4 words
INFO: ngram_search_fwdflat.c(951): 163 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 5478 senones evaluated (74/fr)
INFO: ngram_search_fwdflat.c(955): 3311 channels searched (44/fr)
INFO: ngram_search_fwdflat.c(957): 303 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 153 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.014 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .47
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 17 nodes, 14 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:47:72) = -474236
INFO: ps_lattice.c(1405): Joint P(O,S) = -477749 P(S|O) = -3513
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:24.075 MyApp[3103:6407] Pocketsphinx heard “BACK” with a score of (-3513) and an utterance ID of 000000004.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-6307)
2012-10-12 15:17:24.076 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:24.077 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-6307”;
}
)
2012-10-12 15:17:24.078 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:24.079 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:24.080 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:24.081 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:24.082 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:24.083 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:24.084 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:24.154 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:24.155 MyApp[3103:6407] Listening.
2012-10-12 15:17:24.156 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:24.399 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:30.298 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:30.299 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:31.771 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:31.772 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:31.863 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:31.864 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 903 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 7891 senones evaluated (93/fr)
INFO: ngram_search_fwdtree.c(1553): 4114 channels searched (48/fr), 162 1st, 3667 last
INFO: ngram_search_fwdtree.c(1557): 964 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 143 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.084 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.57 wall 1.852 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 178 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 8884 senones evaluated (105/fr)
INFO: ngram_search_fwdflat.c(955): 5913 channels searched (69/fr)
INFO: ngram_search_fwdflat.c(957): 417 words searched (4/fr)
INFO: ngram_search_fwdflat.c(959): 198 word transitions (2/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.009 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.013 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .56
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 17 nodes, 14 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:56:83) = -553254
INFO: ps_lattice.c(1405): Joint P(O,S) = -557314 P(S|O) = -4060
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:31.877 MyApp[3103:6407] Pocketsphinx heard “NEXT” with a score of (-4060) and an utterance ID of 000000005.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-7700)
2012-10-12 15:17:31.879 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:31.879 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-7700”;
}
)
2012-10-12 15:17:31.881 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:31.881 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:31.882 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:31.883 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:31.884 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:31.885 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:31.886 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:31.957 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:31.958 MyApp[3103:6407] Listening.
2012-10-12 15:17:31.960 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:32.201 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:41.665 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:41.666 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:44.030 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:44.031 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:44.123 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:44.125 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 1714 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 11436 senones evaluated (67/fr)
INFO: ngram_search_fwdtree.c(1553): 4784 channels searched (27/fr), 334 1st, 3903 last
INFO: ngram_search_fwdtree.c(1557): 1809 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 158 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.12 CPU 0.069 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 2.47 wall 1.443 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 285 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 8984 senones evaluated (53/fr)
INFO: ngram_search_fwdflat.c(955): 5598 channels searched (32/fr)
INFO: ngram_search_fwdflat.c(957): 556 words searched (3/fr)
INFO: ngram_search_fwdflat.c(959): 219 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.008 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.02 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .141
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 19 nodes, 15 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:141:169) = -913516
INFO: ps_lattice.c(1405): Joint P(O,S) = -919246 P(S|O) = -5730
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:44.144 MyApp[3103:6407] Pocketsphinx heard “NEXT” with a score of (-5730) and an utterance ID of 000000006.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-15170)
2012-10-12 15:17:44.145 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:44.146 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-15170”;
}
)
2012-10-12 15:17:44.147 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:44.148 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:44.149 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:44.150 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:44.151 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:44.151 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:44.152 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:44.214 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:44.216 MyApp[3103:6407] Listening.
2012-10-12 15:17:44.218 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:44.741 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:44.742 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:46.448 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:46.449 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:46.538 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:46.539 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 1013 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 6174 senones evaluated (63/fr)
INFO: ngram_search_fwdtree.c(1553): 2456 channels searched (25/fr), 188 1st, 1946 last
INFO: ngram_search_fwdtree.c(1557): 1067 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 118 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.08 CPU 0.085 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.81 wall 1.844 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(951): 182 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 4372 senones evaluated (45/fr)
INFO: ngram_search_fwdflat.c(955): 2361 channels searched (24/fr)
INFO: ngram_search_fwdflat.c(957): 261 words searched (2/fr)
INFO: ngram_search_fwdflat.c(959): 102 word transitions (1/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.008 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.008 xRT
INFO: ngram_search.c(1217): not found in last frame, using .96 instead
INFO: ngram_search.c(1269): lattice start node .0 end node .84
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 20 nodes, 10 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:84:96) = -617330
INFO: ps_lattice.c(1405): Joint P(O,S) = -617372 P(S|O) = -42
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.002 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:46.549 MyApp[3103:6407] Pocketsphinx heard “BACK” with a score of (-42) and an utterance ID of 000000007.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: BACK (-10580)
2012-10-12 15:17:46.551 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:46.551 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = BACK;
Score = “-10580”;
}
)
2012-10-12 15:17:46.552 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:46.553 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:46.554 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:46.555 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:46.556 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:46.557 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:46.557 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:46.723 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:46.725 MyApp[3103:6407] Listening.
2012-10-12 15:17:46.726 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:50.129 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:50.130 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:51.647 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:51.648 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:51.739 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:51.741 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 836 words recognized (11/fr)
INFO: ngram_search_fwdtree.c(1551): 6832 senones evaluated (88/fr)
INFO: ngram_search_fwdtree.c(1553): 3456 channels searched (44/fr), 148 1st, 3050 last
INFO: ngram_search_fwdtree.c(1557): 894 words for which last channels evaluated (11/fr)
INFO: ngram_search_fwdtree.c(1560): 113 candidate words for entering last phone (1/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.089 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.62 wall 2.077 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 5 words
INFO: ngram_search_fwdflat.c(951): 209 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(953): 7784 senones evaluated (100/fr)
INFO: ngram_search_fwdflat.c(955): 5185 channels searched (66/fr)
INFO: ngram_search_fwdflat.c(957): 394 words searched (5/fr)
INFO: ngram_search_fwdflat.c(959): 234 word transitions (3/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.01 CPU 0.013 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.010 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .46
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 20 nodes, 21 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:46:76) = -530018
INFO: ps_lattice.c(1405): Joint P(O,S) = -530996 P(S|O) = -978
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:51.751 MyApp[3103:6407] Pocketsphinx heard “NEXT” with a score of (-978) and an utterance ID of 000000008.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: NEXT (-6035)
2012-10-12 15:17:51.752 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:51.752 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = NEXT;
Score = “-6035”;
}
)
2012-10-12 15:17:51.753 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:51.754 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:51.755 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:51.756 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:51.757 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:51.758 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:51.759 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:51.831 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:51.834 MyApp[3103:6407] Listening.
2012-10-12 15:17:51.838 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:17:52.066 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:17:55.047 MyApp[3103:6407] Speech detected…
2012-10-12 15:17:55.048 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectSpeech] Pocketsphinx has detected speech.
2012-10-12 15:17:56.477 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:17:56.477 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidDetectFinishedSpeech] Pocketsphinx has detected a second of silence, concluding an utterance.
2012-10-12 15:17:56.569 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
2012-10-12 15:17:56.570 MyApp[3103:6407] Processing speech, please wait…
INFO: cmn_prior.c(121): cmn_prior_update: from
INFO: cmn_prior.c(139): cmn_prior_update: to
INFO: ngram_search_fwdtree.c(1549): 756 words recognized (10/fr)
INFO: ngram_search_fwdtree.c(1551): 3970 senones evaluated (52/fr)
INFO: ngram_search_fwdtree.c(1553): 1324 channels searched (17/fr), 146 1st, 949 last
INFO: ngram_search_fwdtree.c(1557): 795 words for which last channels evaluated (10/fr)
INFO: ngram_search_fwdtree.c(1560): 51 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.07 CPU 0.086 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.53 wall 1.990 xRT
INFO: ngram_search_fwdflat.c(316): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(951): 120 words recognized (2/fr)
INFO: ngram_search_fwdflat.c(953): 228 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(955): 174 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(957): 174 words searched (2/fr)
INFO: ngram_search_fwdflat.c(959): 58 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(962): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(965): fwdflat 0.01 wall 0.007 xRT
INFO: ngram_search.c(1269): lattice start node .0 end node .46
INFO: ngram_search.c(1297): Eliminated 0 nodes before end node
INFO: ngram_search.c(1402): Lattice has 14 nodes, 2 links
INFO: ps_lattice.c(1367): Normalizer P(O) = alpha(:46:75) = -483258
INFO: ps_lattice.c(1405): Joint P(O,S) = -483258 P(S|O) = 0
INFO: ngram_search.c(891): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(894): bestpath 0.00 wall 0.000 xRT
2012-10-12 15:17:56.578 MyApp[3103:6407] Pocketsphinx heard “” with a score of (0) and an utterance ID of 000000009.
The unpacked ternary operator evaluates as true in the HLW version of the nbest path->score assignment. If you are seeing this message at a time in which something buggy is happening, you might want to try opening ps_lattice.c and commenting out the HLW version of the math and replacing it with either one of the two commented-out versions that precede it.
NBEST 1: (null) (-5777)
2012-10-12 15:17:56.579 MyApp[3103:6407] Checking and resetting all audio session settings.
2012-10-12 15:17:56.579 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidReceiveNBestHypothesisArray:] hypothesisArray is (
{
Hypothesis = “(null)”;
Score = “-5777”;
}
)
2012-10-12 15:17:56.580 MyApp[3103:6407] audioCategory is correct, we will leave it as it is.
2012-10-12 15:17:56.582 MyApp[3103:6407] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:17:56.583 MyApp[3103:6407] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:17:56.584 MyApp[3103:6407] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:17:56.585 MyApp[3103:6407] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:17:56.585 MyApp[3103:6407] Setting the variables for the device and starting it.
2012-10-12 15:17:56.586 MyApp[3103:6407] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:17:56.660 MyApp[3103:6407] Started audio output unit.
2012-10-12 15:17:56.662 MyApp[3103:6407] Listening.
2012-10-12 15:17:56.663 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:19:41.779 MyApp[3103:6f4b] -[PDFPresentationView configurePage:forIndex:]0 page index: 6, current 5
2012-10-12 15:19:41.783 MyApp[3103:6f4b] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:19:42.884 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:19:47.447 MyApp[3103:1743] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_046 ———————– Stopping
2012-10-12 15:19:47.450 MyApp[3103:6407] Stopping audio unit.
2012-10-12 15:19:47.549 MyApp[3103:6407] Audio Output Unit stopped, cleaning up variable states.
INFO: ngram_search_fwdtree.c(430): TOTAL fwdtree 0.71 CPU 0.083 xRT
INFO: ngram_search_fwdtree.c(433): TOTAL fwdtree 16.40 wall 1.916 xRT
INFO: ngram_search_fwdflat.c(185): TOTAL fwdflat 0.06 CPU 0.007 xRT
INFO: ngram_search_fwdflat.c(188): TOTAL fwdflat 0.08 wall 0.010 xRT
INFO: ngram_search.c(320): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(323): TOTAL bestpath 0.00 wall 0.000 xRT
2012-10-12 15:19:47.553 MyApp[3103:6407] This device is not recording, so first we will set its recording status to 0
2012-10-12 15:19:47.554 MyApp[3103:6407] The audio unit is running so we are going to dispose of its instance
2012-10-12 15:19:47.556 MyApp[3103:6407] No longer listening.
2012-10-12 15:19:47.556 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStopListening] Pocketsphinx has stopped listening.
2012-10-12 15:19:47.561 MyApp[3103:1743] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_046 ———————– Stopping finished
2012-10-12 15:19:49.516 MyApp[3103:907] -[PDFPresentationView dealloc]: <PDFPresentationView: 0x1fd4f840; frame = (0 0; 320 568); autoresize = W+H; gestureRecognizers = ; layer = >
2012-10-12 15:19:49.517 MyApp[3103:907] -[PresentationBaseView dealloc]0
2012-10-12 15:19:49.525 MyApp[3103:907] -[PDFPresentationView dealloc]: <PDFPresentationView: 0x1fd7a100; frame = (0 0; 1280 720); clipsToBounds = YES; alpha = 0; autoresize = W+H; layer = >
2012-10-12 15:19:49.526 MyApp[3103:907] -[PresentationBaseView dealloc]1
2012-10-12 15:20:52.666 MyApp[3103:907] +[DocumentHelper documentTypeFromUrl:] pathExtension: pdf
2012-10-12 15:20:52.669 MyApp[3103:907] -[PresentationBaseView ensureExternalPresentationView]0 <ExternalScreenWindow: 0x1fd60920; baseClass = UIWindow; frame = (0 0; 1280 720); layer = >
2012-10-12 15:20:52.679 MyApp[3103:907] -[PDFPresentationView configurePage:forIndex:]0 page index: 0, current 0
2012-10-12 15:20:52.683 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.31, minimumZoomScale: 0.31
2012-10-12 15:20:52.734 MyApp[3103:907] -[PageScrollView setView:size:] Starting at zoomScale: 0.94, minimumZoomScale: 0.94
2012-10-12 15:20:53.185 MyApp[3103:6d8f] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting
2012-10-12 15:20:53.186 MyApp[3103:6d8f] The audio session has already been initialized but we will override its properties.
2012-10-12 15:20:53.187 MyApp[3103:6d8f] Checking and resetting all audio session settings.
2012-10-12 15:20:53.188 MyApp[3103:6d8f] audioCategory is correct, we will leave it as it is.
2012-10-12 15:20:53.189 MyApp[3103:6d8f] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:20:53.190 MyApp[3103:6d8f] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:20:53.191 MyApp[3103:6d8f] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:20:53.192 MyApp[3103:6d8f] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:20:53.193 MyApp[3103:6d8f] AudioSessionManager startAudioSession has reached the end of the initialization.
2012-10-12 15:20:53.194 MyApp[3103:6d8f] Exiting startAudioSession.
2012-10-12 15:20:53.196 MyApp[3103:195f] Recognition loop has started
2012-10-12 15:20:53.197 MyApp[3103:6d8f] __43-[SpeechRecognizer enableVoiceRecognition:]_block_invoke_0 ———————– Starting finished
INFO: cmd_ln.c(706): Parsing command line:
\
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel \
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic \
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app \
-lw 6.500000 \
-maxhmmpf 3000
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-argfile
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-bghist no no
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-compallsen no no
-debug 0
-dict /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app
-input_endian little little
-jsgf
-kdmaxbbi -1 -1
-kdmaxdepth 0 0
-kdtree
-latsize 5000 5000
-lda
-ldadim 0 0
-lextreedump 0 0
-lifter 0 0
-lm /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.languagemodel
-lmctl
-lmname default default
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf -1 3000
-maxnewoov 20 20
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-5 1.000000e-05
-pl_window 0 0
-rawlogdir
-remove_dc no no
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-usewdphones no no
-uw 1.0 1.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02
INFO: cmd_ln.c(706): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 47 \
-varnorm no
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 47
-dither no no
-doublebw no no
-feat 1s_c_d_dd 1s_c_d_dd
-frate 100 100
-input_endian little little
-lda
-ldadim 0 0
-lifter 0 0
-logspec no no
-lowerf 133.33334 1.000000e+00
-ncep 13 13
-nfft 512 512
-nfilt 40 20
-remove_dc no yes
-round_filters yes no
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec 0-12/13-25/26-38
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 4.000000e+03
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.500000e-02
INFO: acmod.c(250): Parsed model-specific feature parameters from /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/feat.params
INFO: feat.c(713): Initializing feature stream to type: ‘1s_c_d_dd’, ceplen=13, CMN=’current’, VARNORM=’no’, AGC=’none’
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(171): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-sen, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/transition_matrices
INFO: acmod.c(125): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(294): 256×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(995): Loading senones from dump file /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/sendump
INFO: s2_semi_mgau.c(1019): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1114): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1391): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4110 * 20 bytes (80 KiB) for word entries
INFO: dict.c(332): Reading main dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/OpenEars-NextBack.dic
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(335): 3 words read
INFO: dict.c(341): Reading filler dictionary: /var/mobile/Applications/A9B131F0-B601-4B62-A5EE-F0CBA6A9182E/MyApp.app/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(400): Building PID tables for dictionary
INFO: dict2pid.c(408): Allocating 50^3 * 2 bytes (244 KiB) for word-initial triphones
INFO: dict2pid.c(135): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(199): Allocated 30200 bytes (29 KiB) for single-phone word triphones
INFO: ngram_model_arpa.c(488): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa.c(143): Reading unigrams
INFO: ngram_model_arpa.c(528): 4 = #unigrams created
INFO: ngram_model_arpa.c(204): Reading bigrams
INFO: ngram_model_arpa.c(547): 4 = #bigrams created
INFO: ngram_model_arpa.c(548): 3 = #prob2 entries
INFO: ngram_model_arpa.c(558): 3 = #bo_wt2 entries
INFO: ngram_model_arpa.c(302): Reading trigrams
INFO: ngram_model_arpa.c(573): 2 = #trigrams created
INFO: ngram_model_arpa.c(574): 2 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 2 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 132
INFO: ngram_search_fwdtree.c(338): after: 2 root, 4 non-root channels, 11 single-phone words
INFO: ngram_search_fwdflat.c(167): fwdflat: min_ef_width = 4, max_sf_win = 25
2012-10-12 15:20:53.307 MyApp[3103:195f] Starting openAudioDevice on the device.
2012-10-12 15:20:53.308 MyApp[3103:195f] Audio unit wrapper successfully created.
2012-10-12 15:20:53.317 MyApp[3103:195f] Set audio route to AirTunes
2012-10-12 15:20:53.317 MyApp[3103:195f] Checking and resetting all audio session settings.
2012-10-12 15:20:53.319 MyApp[3103:195f] audioCategory is correct, we will leave it as it is.
2012-10-12 15:20:53.319 MyApp[3103:195f] bluetoothInput is correct, we will leave it as it is.
2012-10-12 15:20:53.320 MyApp[3103:195f] categoryDefaultToSpeaker is correct, we will leave it as it is.
2012-10-12 15:20:53.323 MyApp[3103:195f] preferredBufferSize is correct, we will leave it as it is.
2012-10-12 15:20:53.324 MyApp[3103:195f] preferredSampleRateCheck is correct, we will leave it as it is.
2012-10-12 15:20:53.325 MyApp[3103:195f] Setting the variables for the device and starting it.
2012-10-12 15:20:53.325 MyApp[3103:195f] Looping through ringbuffer sections and pre-allocating them.
2012-10-12 15:20:58.968 MyApp[3103:195f] 15:20:58.968 AUIOClient_StartIO failed (2003329396)
2012-10-12 15:20:58.968 MyApp[3103:195f] Couldn’t start audio unit output: 2003329396
2012-10-12 15:20:58.969 MyApp[3103:195f] startRecording failed
2012-10-12 15:20:58.970 MyApp[3103:195f] Calibration has started
2012-10-12 15:20:58.970 MyApp[3103:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
2012-10-12 15:20:58.972 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartCalibration] Pocketsphinx calibration has started.
2012-10-12 15:21:01.205 MyApp[3103:195f] cont_ad_calib failed
2012-10-12 15:21:01.207 MyApp[3103:195f] Calibration has completed
2012-10-12 15:21:01.207 MyApp[3103:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
2012-10-12 15:21:01.209 MyApp[3103:195f] Project has these words in its dictionary:
BACK
NEXT
NEXT(2)
2012-10-12 15:21:01.209 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidCompleteCalibration] Pocketsphinx calibration is complete.
2012-10-12 15:21:01.210 MyApp[3103:195f] Listening.
2012-10-12 15:21:01.211 MyApp[3103:195f] cont_ad_read failed
2012-10-12 15:21:01.211 MyApp[3103:907] -[SpeechRecognizer pocketsphinxDidStartListening] Pocketsphinx is now listening.
2012-10-12 15:21:01.212 MyApp[3103:907] -[SpeechRecognizer pocketSphinxContinuousSetupDidFail] Setting up the continuous recognition loop has failed for some reason, please turn on OPENEARSLOGGING in OpenEarsConfig.h to learn more.
(lldb)
-
AuthorPosts