Menu

Accurancy on PocketSphinx

Help
flash shen
2010-09-19
2012-09-22
  • flash shen

    flash shen - 2010-09-19

    I use PocketSphinx for name recognition. There are about 4000 different names,
    and the target accurancy is 90%. Unfortunately at the moment, it's only 65% in
    accurancy using PocketSphinx with the acoustic model hub4wsj_sc_8k, and
    language model in JSFG model.
    I wonder if PocketSphinx can achieve the accurancy of 90% for such 4000
    command size. And if could, what can I do to improve the accurancy? Many
    thanks!

     
  • flash shen

    flash shen - 2010-09-25

    Thank you nshmyrev.

    I'm new in speech recognition, and don't know what to do now to improve the
    accurancy.

    I've tried to cluster the names into classes in which the names have similar
    pronunciation, but this doesn't make sense.

    By ways, do you mean there's no possibility to achieve 90% accuracy in a such
    task? If possible, what can I do next?

    Thank you~

     
  • Nickolay V. Shmyrev

    By ways, do you mean there's no possibility to achieve 90% accuracy in a
    such task? If possible, what can I do next?

    There is no magic bullet here. Read the articles mentioned above, try to
    implement what's described in them.

     
  • prabhu

    prabhu - 2010-10-13

    hi...

    I trained an hour of voice for US-English as continuous speech recognition..
    when I used pocketsphinx for decoding.. It is giving only numbers not words /
    vocabulary.. zero accuracy..

    Using same AM, LM and dict.. i decoded by sphinx3.. Its giving very good
    accuracy.. Please tell me whats wrong with pocketsphinx

    actually i sent an email to u along with path to be download..

     
  • Nickolay V. Shmyrev

    i sent an email to u along with path to be download..

    Sorry, I don't remember I got anything like that. Probably it went to spam.
    Can you share them again? Preferably don't contact me by email, post links
    here.

     
  • cornelyus

    cornelyus - 2010-10-27

    hello ximigou.. how do you measure that kind of accuracy?

     
  • flash shen

    flash shen - 2010-10-31

    I use 3 small test datasets to measure the accuracy. Each dataset cotains 100
    names readed by one person. So there are 3 persons and 300 names. The accuracy
    is around 60%-65% when using different acoustic models, but not much
    difference.

     

Log in to post a comment.