CFP last date
22 April 2024
Reseach Article

Speaker Recognition using VQ and DTW

Published on August 2012 by Maruti Limkar, B. Rama Rao, Vidya Sagvekar
International Conference on Advances in Communication and Computing Technologies 2012
Foundation of Computer Science USA
ICACACT - Number 3
August 2012
Authors: Maruti Limkar, B. Rama Rao, Vidya Sagvekar
e21b4bbd-3501-43b4-8624-3adcedd64ecb

Maruti Limkar, B. Rama Rao, Vidya Sagvekar . Speaker Recognition using VQ and DTW. International Conference on Advances in Communication and Computing Technologies 2012. ICACACT, 3 (August 2012), 18-20.

@article{
author = { Maruti Limkar, B. Rama Rao, Vidya Sagvekar },
title = { Speaker Recognition using VQ and DTW },
journal = { International Conference on Advances in Communication and Computing Technologies 2012 },
issue_date = { August 2012 },
volume = { ICACACT },
number = { 3 },
month = { August },
year = { 2012 },
issn = 0975-8887,
pages = { 18-20 },
numpages = 3,
url = { /proceedings/icacact/number3/7982-1018/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on Advances in Communication and Computing Technologies 2012
%A Maruti Limkar
%A B. Rama Rao
%A Vidya Sagvekar
%T Speaker Recognition using VQ and DTW
%J International Conference on Advances in Communication and Computing Technologies 2012
%@ 0975-8887
%V ICACACT
%N 3
%P 18-20
%D 2012
%I International Journal of Computer Applications
Abstract

Speaker recognition is a process where a person is recognized on the basis of his/her voice signals. In this paper we provide a brief overview for evolution of pattern classification technique used in speaker recognition. Also discussed propose process to modeling a speaker recognition system, which include pre-processing phase, feature extraction phase and pattern classification phase. Linear Prediction Cepstrum Coefficient (LPCC) and Mel Frequency Cepstrum Coefficient (MFCC) are used as the features for text dependent speaker recognition in this system and the experiments compare the recognition rate of LPCC, MFCC or a combination of LPCC and MFCC through using Vector Quantization (VQ) and Dynamic Time Warping (DTW) to recognize a speaker's identity. It proves that the combination of LPCC and MFCC has a higher recognition rate.

References
  1. Campbell J. P,"Speaker Recogniton :ATutorial", Proc. of the IEEE,vol. 85,no. 9,pp. 1437-1462,sep. 1997.
  2. Sadaoki Furui. , "Recent advances in speaker recognition",Pattern Recognition Letters. 1997,18 (9): 859-72.
  3. ZhiyouMa,"Further Extraction for Speaker Recognition", IEEE International Conference on Systems, Man and Cybernetics,153- 158,2003.
  4. Lawrence R. Rabiner. , "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition", Proceedings of the IEEE, 77 (2), 1989, p. 257–286.
  5. DengHaojiang,Wangshoujie,XingCangju,LiuQian,"Research of Text-Independent Speaker Recognition Using Clustering Statistic",Jumal of Circuits and Systems,2001.
  6. Reynolds, D. A. and Rose, R. C. "Robust text independent speaker identification using Gaussian mixture speaker model", IEEE Trans. Speech Audio Process,3,1995,pp 72-83.
  7. Sadoki Furui, "Cepstral analysis technique for automatic speaker verification", IEEE Trans. ASSP 29,1981, pages 254-272.
  8. F. K. Soong,A. E. Rosenberg,L. R. Rabiner and B. H. Juang, "A Vector Quantization approach to Speaker Recognition", Florida: ICASSP Vol. 1, 1985, pp. 387-390.
Index Terms

Computer Science
Information Sciences

Keywords

Speaker Recognition Lpcc Mfcc Vq Dtw