Presentation 2003/4/18
Speaker Recognition System Based on GMM using LPC-cepstrum and Pitch
Eric Simancas Acevedo, Akira Kurematsu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents the experimental comparison of a speaker recognition system based on Gaussian Mixtures Model (GMM) by reinforcing and enhancing the feature vector characteristics. The baseline system proposed use a GMM with 8 gaussian mixtures with diagonal covariance matrix and for feature vector the LPC-cepstrum coefficients are used. One system is developed to improve the recognition rate by using only voiced part to extract the LPC-cepstrum coefficients. Other system is made reinforcing the feature vector LPC-cepstrum with pitch information. The system is compared with the system enhanced by the feature vector LPC-cepstrum with Cepstral Mean Normalization (CMN). The experimental comparisons of those systems are evaluated in closed and open test using speech data with time difference.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speaker Recognition System (SRS) / Gaussian Mixtures Model (GMM) / Voiced speech / LPC-cepstrum / Pitch / Cepstral Mean Normalization (CMN)
Paper # EA2003-17,SP2003-17
Date of Issue

Conference Information
Committee EA
Conference Date 2003/4/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Engineering Acoustics (EA)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speaker Recognition System Based on GMM using LPC-cepstrum and Pitch
Sub Title (in English)
Keyword(1) Speaker Recognition System (SRS)
Keyword(2) Gaussian Mixtures Model (GMM)
Keyword(3) Voiced speech
Keyword(4) LPC-cepstrum
Keyword(5) Pitch
Keyword(6) Cepstral Mean Normalization (CMN)
1st Author's Name Eric Simancas Acevedo
1st Author's Affiliation SEPI, ESIME Culhuacan, National Polytechnic Institute of Mexico()
2nd Author's Name Akira Kurematsu
2nd Author's Affiliation The University of Electro Communications
Date 2003/4/18
Paper # EA2003-17,SP2003-17
Volume (vol) vol.103
Number (no) 25
Page pp.pp.-
#Pages 6
Date of Issue