oscarjiv91

Forum Replies Created

Viewing 12 posts - 1 through 12 (of 12 total)

  • Author
    Posts
  • in reply to: Gender and Detection #1025355
    oscarjiv91
    Participant

    I tested it with 3 men and 3 women.

    in reply to: Gender and Detection #1025353
    oscarjiv91
    Participant

    Yes, I’m using 2.x acoustic model. Not sure what you mean with “sample size”. I’m testing it with live speech. Also have this problem with children voices.

    in reply to: Gender and Detection #1025348
    oscarjiv91
    Participant

    Yes, is related to different gender voices.

    in reply to: Gender and Detection #1025346
    oscarjiv91
    Participant

    I’m trying to recognize just one name at a time (keyword-spotting)

    btw, I’m generating my model language with this function:

    generateRejectingLanguageModelFromArray:withFilesNamed:withOptionalExclusions:usingVowelsOnly:withWeight:forAcousticModelAtPath:pathToModel

    I’m using Rejecto and RapidEars

    in reply to: Gender and Detection #1025345
    oscarjiv91
    Participant

    Hello again Halle.

    I’m trying to recognize names (John, Brian, etc.) with different voices and accents.

    using only speech related to your language model

    For adaptation, does this mean that I need to record these names with different voices from a list of names I want to recognize? Or can be done recording other words just to “train” the phonemes?

    in reply to: Poor accuracy for spanish language #1025335
    oscarjiv91
    Participant

    I appreciate your help Halle! This was very helpful. Thanks

    in reply to: Poor accuracy for spanish language #1025332
    oscarjiv91
    Participant

    Yes, I’m always setting the Rejecto weight to 2.0. Setting the vadThreshold to 3.0 in spanish, I get more false positives than expected when somebody is talking (especially when there are words with similar vowels), even if there is no background noises. I guess this is an accuracy issue, right?

    in reply to: Poor accuracy for spanish language #1025329
    oscarjiv91
    Participant

    Ok thanks Halle! Will test it more with higher values. I’m using Rejecto btw :)

    in reply to: Poor accuracy for spanish language #1025327
    oscarjiv91
    Participant

    This “sensitivity setting” is the vadThreshold? or another variable used by openears?

    in reply to: Poor accuracy for spanish language #1025325
    oscarjiv91
    Participant

    or training the acoustic model?

    in reply to: Poor accuracy for spanish language #1025324
    oscarjiv91
    Participant

    Thanks for your quick reply.

    The thing is that I need to recognize the words from like 2 meters away, and if I set the vadThreshold with a very high value, it does not recognize the word I want. Adapting the acoustic model would improve the accuracy?

    oscarjiv91
    Participant

    Oh ok. Thanks for your quick response :).

Viewing 12 posts - 1 through 12 (of 12 total)