Volume -I , Issue -V, June 2014

SPEAKER RECOGNITION USING MEL FREQUENCY CEPSTRAL COEFFICIENTAND VECTOR QUANTIZATION

Ravi. G , Prasad Kumar B. M.

In this paper we are going to use Mel Frequency Cepstral Co-efficient (MFCC) and vector Quantization (VQ) methods for feature extraction and feature matching process. Further vector quantization is used to reduce the amount of data to be stored in the database for verification. Here we are going to recognize for the English word “zero” is obtained. The experiment results are analyzed using MATLAB. By using this approach recognition rate is reached up to 89% and distortion reduced to 69%.

Speaker Recognition, feature extraction, feature matching, MFCC, VQ.

1. Roucos, S. Berouti, M. Bolt, Beranek and Newman, Inc., Cambridge, MA; “Theapplication of probability density estimation to text-independent speaker identification” IEEE International Conference on Acoustics, Speech, and Signal Processing,ICASSP 82. Volume: 7, On page(s): 1649-
2. Campbell, J.P., Jr.; “Speaker recognition: a tutorial” Proceedings of the IEEE Volume85, Issue 9, Sept.1997 Page(s):1437 – 1462.
3. Control, Communications and Signal Processing, Proceedings of IEEE 2004 Page(s):631 – 634.
4. 192, April 1994
5. Seddik, H.; Rahmouni, A.; Sayadi, M.; “Text independent speaker recognition using the Mel frequency cepstral coefficients and a neural network classifier” First International Symposium on
6. 1652. Publication Date: May 1982
7. Moureaux, J.M., Gauthier P, Barlaud, M and Bellemain P.”Vector quantization of rawSAR data”,IEEE International Conference on Acoustics, Speech, and Signal Processing Volume 5, Page(s):189 -
8. Childers, D.G.; Skinner, D.P.; Kemerait, R.C.; “The cepstrum: Aguide to processing”Proceedings of the IEEE Volume 65, Issue 10, Oct. 1977 Page(s):1428 – 1443