Performance study of vector quantization methods (k-means, GMM) for arabic isolated word recognition system based on DHMM

Author

Cherifa, S. ; Messaoud, R. ; Narima, Zermi ; Houcine, Bourouba

Author_Institution

Lab. d´Autom. et Signaux d´Annaba (LASA), Univ. Badji Mokhtar de Annaba, Annaba, Algeria

fYear

2013

fDate

22-24 June 2013

Firstpage

1

Lastpage

4

Abstract

This article present several techniques used in the design of an isolated Arabic words recognition system based on the discrete Hidden Markov Model. We present the results of an experimental study aimed at finding the effect of the quantization methods (k-means and GMM) on the recognition performance. we used in analysis phase Mel Frequency Cepstral Coefficients (MFCC), although experiments are carried out for the choice of the optimal parameters of the system. Good results are obtained using a GMM method.

Keywords

Gaussian processes; hidden Markov models; natural language processing; pattern clustering; vector quantisation; word processing; Arabic isolated word recognition system; DHMM; GMM method; MFCC; Mel frequency cepstral coefficients; discrete hidden Markov model; k-means method; vector quantization; Computational modeling; Hidden Markov models; Mel frequency cepstral coefficient; Speech; Speech recognition; Support vector machine classification; Vectors; Gaussian mixture models (GMM); Mel Frequency Cepstral Coefficients (MFC); discret hidden markov model(DHMM); k-means; speech recognition system (SRS);

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology (WCCIT), 2013 World Congress on

Conference_Location

Sousse

Print_ISBN

978-1-4799-0460-0

Type

conf

DOI

10.1109/WCCIT.2013.6618722

Filename

6618722