Menu

Pocketsphinx feature-vad branch

Help
creative64
2014-03-05
2014-03-28
  • creative64

    creative64 - 2014-03-05

    Hi,

    How is feature-vad branch different from the regular pocketsphinx ? Will this be merged into the next PS release ?

    Thanks,

     
  • Nickolay V. Shmyrev

    How is feature-vad branch different from the regular pocketsphinx ?

    Feature-vad implements proper speech processing API that doesn't degrade in presense of silence inside the utterance.

    Will this be merged into the next PS release ?

    Yes

     
  • creative64

    creative64 - 2014-03-06

    So you mean the current Pocketsphinx doesn't handle presence of silence inside utterance properly ! Could you elaborate a bit please.

    Thanks.

     
  • Nickolay V. Shmyrev

    So you mean the current Pocketsphinx doesn't handle presence of silence inside utterance properly

    Yes

    Could you elaborate a bit please.

    If there is a lot of silence CMN is not estimated properly and the accuracy drops drastically.

     
  • Pankaj

    Pankaj - 2014-03-07

    Hi,

    Is the Feature-VAD branch being developed only for the Android Version or will it affect the Desktop version also.

    I think the current VAD in desktop version passes on only speech segments for further processing.

    How will the new Feature VAD be different.

    Regards
    Pankaj

     
  • Nickolay V. Shmyrev

    Is the Feature-VAD branch being developed only for the Android Version or will it affect the Desktop version also. I think the current VAD in desktop version passes on only speech segments for further processing.

    Feature vad is for both desktop and android. The advantage of feature-vad is that it applies after noise removal, so it's more robust to noise than the current VAD.

     
  • Pankaj

    Pankaj - 2014-03-07

    Hi Nicole,

    In the current version 0.8,(and also previous versions) of VAD, VAD only gives speech segments to fe_process_raw function, so I am not able to understand what you mean by "presence of silence in utterance", as you have mentioned earlier in this thread.

    You have also talked about accuracy dropping drastically. Was this problem always there in pocketsphinx? I have extensively used 0.6, 0.7 versions of pocketsphinx in FSG mode and I never observed any major difference in accuracy.

     
  • Nickolay V. Shmyrev

    In the current version 0.8,(and also previous versions) of VAD, VAD only gives speech segments to fe_process_raw function, so I am not able to understand what you mean by "presence of silence in utterance", as you have mentioned earlier in this thread.

    When I wrote "utterance" I mean batch processing because only batch processing deals with utterances. For continuous processing with VAD this was less a problem, but it affected trainign where VAD was not used.

    For continuous processing the noise-robustness of the VAD is an issue. Feature-vad is noise-robust, original energy-based VAD is not.

     
  • Serotonergic

    Serotonergic - 2014-03-27

    ok, so seems like the feature-vad branch has been deleted in the svn repo...I'm also looking to get silence within an utterance detected in pocketsphinx. Would appreciate some pointers on this

     
  • Nickolay V. Shmyrev

    It is merged in trunk

     
    • Serotonergic

      Serotonergic - 2014-03-27

      Thanks....

       

Log in to post a comment.