Menu

how to decide the values cminit?

Help
2017-03-21
2017-03-21
  • Tania Mendonca

    Tania Mendonca - 2017-03-21

    When i try to decode the audio file the cmn value updates many times?
    how to update the cmn value only once?
    how to choose the cminit values?

     
    • Nickolay V. Shmyrev

      When i try to decode the audio file the cmn value updates many times?

      Yes.

      how to update the cmn value only once?

      Modify the source code.

      how to choose the cminit values?

      Select average value from the test database.

       
  • Tania Mendonca

    Tania Mendonca - 2017-03-21

    Is it during pocketsphinx batch the cmn value is updated only once?
    While in continuous the cmn is updated many times because the audio is read sequentially ?
    Does changing the cmn value improve the recognition accuracy?

    The default value for cminit is 40,3,-1
    So if i try to decode 2 audio say
    Audio. 1 cmn value. 57 -11(and the reamainin 11 values
    Auduo 2 cmn value 49 -9 (and the remaining 11 values)
    So I need need to choose a cminit of 53,10( and the remaining 11 values averages)
    So that the accuracy will improve?( Please correct me if I'm wrong)
    Thanks in advance

     
    • Nickolay V. Shmyrev

      Is it during pocketsphinx batch the cmn value is updated only once?

      No, it is recomputed for every utterance.

      While in continuous the cmn is updated many times because the audio is read sequentially ?

      Yes, it is updated once in 10 seconds or on silence.

      Does changing the cmn value improve the recognition accuracy?

      Yes if audio is not very diverse.

      The default value for cminit is 40,3,-1

      So I need need to choose a cminit of 53,10( and the remaining 11 values averages)
      So that the accuracy will improve?( Please correct me if I'm wrong)

      2 utterances are not sufficient to estimate the stats, you need 20 at least. But the idea is correct. Accuracy will improve.

       

Log in to post a comment.