In order to recognize speech, a Speech Recognition Engine (SRE) requires two types of files: An Acoustic Model and a Language Model or Grammar.

An Acoustic Model, is created by taking a very large number of transcribed speech recordings (called a Speech Corpus) and 'compiling' them into statistical representations of the sounds that make up each word.

© 2005-2009 VoxForge; Legal: Terms and Conditions

SourceForge.net Logo