15-04-2010, 10:13 PM
Text-Independent Speaker Verification
INTRODUCTION
Among the most popular measurements for biometric identification are fingerprint, face, and voice.the speaker
recognition area has a long and rich scientific basis with over
30 years of research, development, and evaluations.
a speaker verification system:
[attachment=3216]
step 1:
It consists in extracting parameters
from the speech signal to obtain a representation
suitable for statistical modeling as such models are extensively
used in most state-of-the-art speaker verification systems.
Step2:
obtaining a statistical model from the parameters.
SPEECH PARAMETERIZATION:
It involves transforming the speech signal to a set of feature vectors. Most of such systems relies on a cepstral representation of
speech.
For more details, refer this pdf:
http://cs.toronto.edu/~gpenn/csc2518/bimbot-etal04.pdf
http://neural.cs.nthu.edu.tw/jang/books/...akerId.pdf