PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop

cmusphinx cmusphinx Last update: Jun 05, 2022

PocketSphinx 5prealpha

This is PocketSphinx, one of Carnegie Mellon University's open source largevocabulary, speaker-independent continuous speech recognition engine.

THIS IS A RESEARCH SYSTEM. This is also an early release of a researchsystem. We know the APIs and function names are likely to change, and thatseveral tools need to be made available to make this all complete. With yourhelp and contributions, this can progress in response to the needs and patchesprovided.

Please see the LICENSE file for terms of use.

Prerequisites

You must have SphinxBase, which you can download fromhttp://cmusphinx.sourceforge.net. Download and unpack it to the same parentdirectory as PocketSphinx, so that the configure script and project files canfind it. On Windows, you will need to rename 'sphinxbase-X.Y' (where X.Y is theSphinxBase version number) to simply 'sphinxbase' for this to work.

Linux/Unix installation

In a unix-like environment (such as linux, solaris etc):

  • Build and optionally install SphinxBase. If you want to usefixed-point arithmetic, you must configure SphinxBase with the--enable-fixed option.

  • If you downloaded directly from the CVS repository, you need to dothis at least once to generate the "configure" file:

    $ ./autogen.sh
  • If you downloaded the release version, or ran autogen.sh at leastonce, then compile and install:

    $ ./configure$ make clean all$ make check$ sudo make install

Xcode Installation (for iPhone)

Pocketsphinx uses the standard unix autogen system, you can build pocketsphinxwith automake given you already built sphinxbase You just need to pass correctconfigure arguments, set compiler path, set sysroot and other options. Afteryou build the code you need to import dylib file into your project and you alsoneed to configure includes for your project to find sphinxbase headers.

You also will have to create a recorder to capture audio with CoreAudio andfeed it into the recognizer.

For details see http://github.com/cmusphinx/pocketsphinx-ios-demo

If you want to quickly start with Pocketsphinx, try OpenEars toolkit whichincludes Pocketsphinx http://www.politepix.com/openears/

Android installation

See http://github.com/cmusphinx/pocketsphinx-android-demo.

MS Windows™ (MS Visual Studio 2012 (or newer - we test with VC++ 2012 Express)

  • load sphinxbase.sln located in sphinxbase directory

  • compile all the projects in SphinxBase (from sphinxbase.sln)

  • load pocketsphinx.sln in pocketsphinx directory

  • compile all the projects in PocketSphinx

MS Visual Studio will build the executables under .\bin\Release or.\bin\Debug (depending on the version you choose on MS Visual Studio),and the libraries under .\lib\Release or .\lib\Build.

Test scripts are forthcoming for Windows.

For up-to-date information, see http://cmusphinx.sourceforge.net.

Open in app Get started ITNEXT Published in ITNEXT You have 2 free member-only stories left this month. Sign up for Medium and get an extra one Kush Kush Follow Apr 15, 2021 · 7 min read · List…

Subscribe to our newsletter