Presentation 1997/3/17
A Neural-Networks-Aided Speaker Recognition System Using Bispectrum
Hideki MAWATARI, Keisuke KAMEYAMA, Yukio KOSUGI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a speaker recognition system using bispectral analysis. The correlation between the harmonic components of the speech signal are evaluated using the bispectrum. The recognition experiments on 6 speakers with their continuous vowels show this system is applicable. The performance of conventional techniques based on the second-order statistics dramatically decreases in a noisy environment. But, in the proposed system the recognition rate doesn't decrease when Gaussian noise is added to the signal, and it also shows high performance even when other speaker's voice is superimposed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) bispectrum / speaker recognition / neural networks / Gaussian noise
Paper # NC96-146
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Neural-Networks-Aided Speaker Recognition System Using Bispectrum
Sub Title (in English)
Keyword(1) bispectrum
Keyword(2) speaker recognition
Keyword(3) neural networks
Keyword(4) Gaussian noise
1st Author's Name Hideki MAWATARI
1st Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Keisuke KAMEYAMA
2nd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
3rd Author's Name Yukio KOSUGI
3rd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
Date 1997/3/17
Paper # NC96-146
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 8
Date of Issue