People,
I need to figure out what is required for achieving speaker independent recognition using
dynamic time warping or other technique but NOT HMM. i know how to derive feature vectors and
this project may be for isolated words or digits only. 
Thanks for helping me out
Iyanu

Ps. I shouldnt mind info on Cepstral Mean Normalization and how to code it in Matlab also.

(You need to be a member of speech-recognition -- send a blank email to speech-recognition-subscribe@yahoogroups.com )