Menu

Which acoustic model to use in Sphinx3?

Help
ashuser
2012-04-30
2012-09-22
  • ashuser

    ashuser - 2012-04-30

    Hi All,
    I have 8kHz, 16 bit audio files and feeding the audio files to
    sphinx3_livepretend sample code. When I use the acoustic model "communicator
    narrowband (8kHz) telephone speech" the recognition results are very poor. But
    when I use "HUB4 (broadcast news) acoustic models - for wideband (16kHz)
    speech" the recognition is very good. http://www.speech.cs.cmu.edu/sphinx/mod
    els/

    My question are as follows:
    a. For telephony speech which model is the best?
    b. How did the recognition work when I used the wrong acoustic models?

     
  • Nickolay V. Shmyrev

    a. For telephony speech which model is the best?

    Communicator

    b. How did the recognition work when I used the wrong acoustic models?

    It's hard to answer this question without the actual audio you were trying to
    decode

     

Log in to post a comment.