VoxForge gathers transcribed speech as a resource for Open Source Speech Recognition Engines.
Currently, the primary focus of VoxForge is on collecting transcribed audio for Command and Control applications on a PC and for Telephony Speech Recognition applications (i.e. IVR - Interactive Voice Response). It is important to note that VoxForge will be collecting English language audio to begin with, with plans of adding other languages in the future.
Submitting speech audio files to VoxForge is a simple process. All you have to do is click the SubmitSpeech link on the menu above to learn how to record your speech and submit your audio files. Once your audio files are submitted, you can move on to the AcousticModels link to learn how to 'compile' your speech audio files into a Speaker Dependent Acoustic Model or modify the VoxForge Speaker Independent Acoustic Model to better recognize your voice.
One of the recent updates with VoxForge is the QuickStart Acoustic Model. This model has been updated, providing users with a smoother and more efficient experience. Overall, VoxForge seems like an excellent tool for those looking to create Acoustic Models to better recognize their voice. With their focus on collecting transcribed speech for use with Open Source Speech Recognition Engines, VoxForge is sure to be a valuable resource for many.
Version 0.1.1: N/A