PocketSphinx 0.6 release

We are pleased to announce the long-awaited PocketSphinx 0.6 release, including SphinxBase 0.6.  This release corresponds to SVN revision 9898.

PocketSphinx is a small-footprint continuous speech recognition system, freely licensed under a simplified BSD license, suitable for handheld and desktop applications.  It features:

  • Cross-platform: Linux, Windows, Mac OS X, iPhoneOS
  • Experimental support for Nokia S60v3 and Windows Mobile
  • Support for semi-continuous, phonetically-tied, and fully continuous acoustic models
  • Model footprint on disk of about 10MB per language
  • Memory footprint under 20MB for medium-vocabulary continuous recognition
  • Trigram language models and JSGF finite-state grammars
  • Acoustic models for English and Mandarin
  • Small language models for English and Mandarin (simplified and traditional characters)
  • Python language bindings
  • GStreamer multimedia framework integration

The release branch can be accessed via Subversion at http://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/branches/pocketsphinx-0.6 – this is the preferred way to access the release, particularly if you are using Windows.

This exact release tag can be accessed at http://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/tags/pocketsphinx-0.6

Source code archives are now available for download at http://sourceforge.net/projects/cmusphinx/

Debian/Ubuntu source packages are available from https://launchpad.net/~dhuggins/+archive/cmusphinx

9 Responses to “PocketSphinx 0.6 release”

  1. Manya Sahakyan says:


    it’s really cool, but somehow we couldn’t find any buld scripts for Nokia (i.e. Symbian) and WinMobile?

    Manya Sahakyan

  2. dhd says:

    Hmm – i think the project files for WinMobile did not make it in, but there is support in the code.

    Look in the “group” directory, there is ABLD.BAT and .mmp files for S60. Not guaranteed to work, but they do have the right files in them…

  3. aris says:

    hi all, can somebody help me out with pocketsphinx?
    I’m trying to integrate it with my symbian application on Nokia s60v3 for my undergraduate thesis.
    The application will record the user’s call conversation, convert it into a .wav file then pocketsphinx will do
    the speech-to-text conversion. Any help or tutorial will be very appreciated. You can contact me through my email dcrow_14@yahoo.com.ph. Thank you and have a good day :)

  4. admin says:

    Aris, to get help you need to describe the problem you have. Just asking for help is senseless, we obviosly want to help you. Please contact us over support channels:


  5. Aris says:

    Thank you for the reply admin.. I’ll contact you asap

  6. getche says:

    any example on how to use it in symbian? It says experimental support…I wanted to make a application that can recognize some words…

  7. Junaid says:

    thanks for providing such api set, it will really solve many problems regarding offline speech processing.

    I m facing a problem with my JSAPI , that is when i dowloaded the JSAPI then the ResultAdapter class is missing. so could you please help me out with this problem and if possible could you please provide me the class file that is ResultAdapter.class.

    Help would be really appreciated.


  8. taf2 says:

    you guys really need to get this project out on git… github maybe? something where more people can help contribute and extend what you have done.