Menu

CMUSphinx is not even able to decode the training voices with accuracy

Help
2018-12-15
2018-12-18
  • Rajdeep Singh

    Rajdeep Singh - 2018-12-15

    My assumption was that if model is tested on files which are a part of training set, WER should be minimal. However this assumption failed. Below are the results:

    We selected 3 audio files on which model has already been trained. Manual transcripts for these audios are:
    so you save the money and then at the one go you (800861022103750_55)
    okay sir sir i will send the request now sir and you will receive the confirmation s m s also (800861022103750_56)
    getting late sir call back and the same number and the reconfirm what happen to your service request sir (800861022103750_57)

    On testing the model on above audio files, following output was generated:
    • since you have one hundred and one don't you (800861022103750_55 -9690)
    • officers have a friend request thousand you will receive a confirmation sms also (800861022103750_56 -17548)
    • getting a check for that i'm the same i'm american so what happened the last census cases (800861022103750_57 -22385)

    Need some help to understand what can be the possible solutions

     
  • Pankaj

    Pankaj - 2018-12-16

    This can also happen when the language model is not appropriate. Can you check the perplexity of your Language model with respect to your test dataset.

     
  • Rajdeep Singh

    Rajdeep Singh - 2018-12-16

    Can you suggest how to check perplexity?

     
  • Pankaj

    Pankaj - 2018-12-16

    Assuming you have installed srilm on your machine and test.txt is the file containing test transcripts and xyz.lm.arpa is your language model then use the command
    ngram -lm xyz.lm.arpa -ppl test.txt > test.ppl
    Generally (not always) smaller the perplexity mumber better would be the performance.

     
  • Rajdeep Singh

    Rajdeep Singh - 2018-12-18

    Thanks Pankaj

     

Log in to post a comment.

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.