Create Acoustic Models

VoxForge

Click the link for your operating system to proceed with instructions on how to record your speech and 'compile' it into a Speaker Dependent Acoustic Model, or 'adapt' the VoxForge Speaker Independent Acoustic Model to better recognize your speech, and then to submit your speech audio recordings to VoxForge for the creation of GPL Speech Corpora and Acoustic Models.

/uploads/aS/La/aSLa7f4Stjjfvpw0AmZ3QA/linuxlogo.jpg

Linux Create Acoustic Model, or adapt the VoxForge Speaker Independent Acoustic Model, and Submit your Speech Audio to VoxForge.

/uploads/rZ/hz/rZhz-LnTJz2hB-Cizr8S7g/Microsoft_Windows.jpg

Windows Create Acoustic Model, or adapt the VoxForge Speaker Independent Acoustic Model, and Submit your Speech Audio to VoxForge.

Comments

Single Speaker Speech Recognition with Hidden Markov Models

By kmaclean - 5/23/2014 - 4 Replies If you are interested in a deeper understanding of how speech recognition works using Python: Single Speaker Speech Recognition with Hidden Markov Models


Username	Password