RapidEars ignoring secondsOfSilenceToDetect – Politepix /forums/topic/rapidears-ignoring-secondsofsilencetodetect/feed/ Tue, 23 Apr 2024 14:42:50 +0000 https://bbpress.org/?v=2.6.9 en-US /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020739 <![CDATA[RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020739 Tue, 08 Apr 2014 01:16:08 +0000 morchella It appears that when setFinalizeHypothesis = FALSE, RapidEars ignores the setting for secondsOfSilenceToDetect. Is this a bug? I don’t need the finalized hypothesis, but I do need to control how long pocketsphinxController waits before considering the utterance ended.

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020742 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020742 Tue, 08 Apr 2014 02:27:54 +0000 Halle Winkler Hello,

RapidEars doesn’t use secondsOfSilenceToDetect. Both live and finalized hypotheses are delivered as soon as they are available.

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020743 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020743 Tue, 08 Apr 2014 02:44:14 +0000 morchella Sorry if I was unclear. There is a rapidEarsDidDetectEndOfSpeech delegate method which appears to always be called 50-300ms after pocketsphinxDidDetectFinishedSpeech. I have observed that these end of speech callbacks are sensitive to secondsOfSilenceToDetect, but only when setFinalizeHypothesis = TRUE.

Is this the intended behavior?

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020744 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020744 Tue, 08 Apr 2014 02:59:30 +0000 Halle Winkler That’s correct – finalizing the hypothesis means that the end of speech is detected and reported, while using live recognition only means that there is no wait for a pause or consequent callback when a pause is detected because a pause at the end of an utterance isn’t used by the engine for determining the hypothesis.

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020745 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020745 Tue, 08 Apr 2014 03:25:40 +0000 morchella Yes, but even when setFinalizeHypothesis = FALSE, the end of speech is still detected and reported. It’s just that the config option (secondsOfSilenceToDetect) is now ignored.

I can work around it, but it seems like incorrect behavior.

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020749 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020749 Tue, 08 Apr 2014 07:25:14 +0000 Halle Winkler I hear what you’re saying, but it is by design. Live mode does not do any kind of waiting for a pause in order to derive state, so if the engine is only operating in live mode, it uses its own logic to determine when is a good time to call an utterance over so that continuous recognition is able to proceed without notable pauses or skips. secondsOfSilenceToDetect and rapidEarsDidDetectEndOfSpeech both refer to pause detection, which isn’t a feature of live mode. It could be documented better, I agree.

I think that if I wanted to use live mode hypotheses and non-live mode utterance logic I’d probably turn finalize on and just ignore its hyp output. The overhead isn’t that heavy.

]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020764 <![CDATA[Reply To: RapidEars ignoring secondsOfSilenceToDetect]]> /forums/topic/rapidears-ignoring-secondsofsilencetodetect/#post-1020764 Tue, 08 Apr 2014 16:41:43 +0000 morchella Okay, thanks Halle, I appreciate the advice!

]]>