DocumentCode
3542047
Title
MFCC and vector quantization for Arabic fricatives speech/speaker recognition
Author
Chelali, Fatma Zohra ; Djeradi, Amar
Author_Institution
Speech Commun. & signal Process. Lab., Univ. of Sci. & Technol. Houari Boumedienne, El Alia, Algeria
fYear
2012
fDate
10-12 May 2012
Firstpage
284
Lastpage
289
Abstract
This article develops a speaker-dependent Arabic phonemes recognition system using MFCC analysis and the VQ-LBG algorithm. The system is examined with and without vector quantization in order to analyze the effect of compression in an acoustic parameterization phase. Our experimental results show that vector quantization using a codebook of size 16 achieves good results compared to the system without quantization for a majority of the phonemes studied.
Keywords
acoustic signal processing; cepstral analysis; natural language processing; speaker recognition; vector quantisation; Arabic fricatives speech-speaker recognition; MFCC analysis; Mel frequency cepstrals coefficients; VQ-LBG algorithm; acoustic parameterization phase; speaker-dependent Arabic phonemes recognition system; vector quantization; Feature extraction; Mel frequency cepstral coefficient; Speaker recognition; Speech; Speech recognition; Vectors; MFCC; VQ; speaker identification; speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia Computing and Systems (ICMCS), 2012 International Conference on
Conference_Location
Tangier
Print_ISBN
978-1-4673-1518-0
Type
conf
DOI
10.1109/ICMCS.2012.6320121
Filename
6320121
Link To Document