Speaker recognition using Mel frequency Cepstral Coefficients (MFCC) and Vector quantization (VQ) techniques

Author

Martinez, Jorge ; Perez, Hector ; Escamilla, Enrique ; Suzuki, Masahisa Mabo

Author_Institution

Nat. Polytech. Inst. (IPN), Mexico City, Mexico

fYear

2012

fDate

27-29 Feb. 2012

Firstpage

248

Lastpage

251

Abstract

This paper presents a fast and accurate automatic voice recognition algorithm. We use Mel frequency Cepstral Coefficient (MFCC) to extract the features from voice and Vector quantization technique to identify the speaker, this technique is usually used in data compression, it allows to model a probability functions by the distribution of different vectors, the results that we achieve were 100% of precision with a database of 10 speakers.

Keywords

feature extraction; probability; speaker recognition; vector quantisation; MFCC; Mel frequency cepstral coefficients; automatic voice recognition algorithm; data compression; feature extraction; probability functions; speaker database; speaker identification; speaker recognition; vector quantization techniques; voice quantization technique; Databases; Filter banks; Mel frequency cepstral coefficient; Speaker recognition; Speech; Speech recognition; Vectors; Discrete Fourier Transform; MFCC; Speech processing; Vector Quantization; Voice; speaker recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Communications and Computers (CONIELECOMP), 2012 22nd International Conference on

Conference_Location

Cholula, Puebla

Print_ISBN

978-1-4577-1326-2

Type

conf

DOI

10.1109/CONIELECOMP.2012.6189918

Filename

6189918