JE> I wonder why, if it is so easy. is it so hard for voice
JE> recognition programs to function reasonably accurately???

MR> My guess why speech recognition is so difficult is basically that there
MR> is a lot of information in the audio signal. There may be any number of
MR> quirks in the voice which can make it unrecognizable for the program
MR> comparing between two individuals. The program has to filter for pitch,
MR> tonal quality, speed, inflection, fricatives, and that's just a start.

MR> One can't simply match up a waveform with another but rather there is a
MR> lot of computation done on-the-fly in analyzing it to extract the
MR> information sought from a forest of waveform information. Text to speech
MR> in contrast is almost child's play since the information is already
MR> known and data is simply output from pre-existing lookup tables.

 I'm sorry. What did you say?  

 Robert

 * SLMR 2.1a * Danger!  Attention Span Exceeded!
--- Platinum Xpress/Win/WINServer v3.0pr5