News for hackers. Stuff that matters.
Re:Whatever Happened to Voice Recognition? by Retric on Monday June 21, 2010 @01:52PM (#1449499)
divided into two parts: the acoustical modeling (from audio file to "phonemes"), and language models

That seems a little off to me. It seems like you would want a list of phoneme probabilities to work with along with how long each sound took etc. Your language model might say “I saw the see past the dune” is less likely than “I saw the sea past the dune” but the more information the language model has to work with the better. For example, dialect impacts both the sounds people use and the words they use.

Also sperating background sounds from a message is easer if you are following the content of the message etc.

There are no comments on this comment yet.