VoxForge / News: Recent posts

VoxForge is pleased to announce the release of a new web-based application for submitting speech. VoxForge collects user-submitted speech audio files for the creation of Acoustic Models for Free and Open Source Speech Recognition Engines.

The new Speech Submission Java applet permits easy submission of you speech. Just read the prompts that are provided and click once to upload your entire submission to VoxForge. A new set of prompts is randomly generated each time you access the application, so you can submit as often as you like.... read more

For details click this link http://www.voxforge.org/home/submitspeech and call the number shown. The Interactive Voice Response System will guide you through the process.

The VoxForge now has a nightly Acoustic Model build at http://www.repository.voxforge1.org/downloads/Nightly_Builds/.

So now when submit your transcribed speech to the Project Web Site, once it is approved, it will be incorporated into the VoxForge Acoustic Model by the next day.

Many thanks to the following users for submitting their Transcribed Speech Audio to VoxForge for the creation of this week's Acoustic Model build (build726):

crxssi
csawtell
kylegoetz
mfread - submitted 10 entries!
pmahoney - submitted 2 entries!
rusty

the VoxForge team

VoxForge was set up to collect transcribed speech to create a GPL Speech Corpus for use with Open Source Speech Recognition Engines. These Speech Audio files are then 'compiled' into Acoustic Models for use with Open Source Speech Recognition engines such as HTK, Julius, CAVS (formerly ISIP), and Sphinx.

This QuickStart download was designed to highlight the use of VoxForge Acoustic Models with Open Source Speech Recognition Engines. We will start with a download that uses the Julius Speech Recognition Engine. ... read more