Presentation 2004/12/14
A stream-weight optimization method based on boosting for multi-stream speaker verification
Taichi ASAMI, Koji IWANO, Sadaoki FURUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes an automatic stream-weight optimization method for speaker verification using multi-stream HMMs. We have already proposed a noise-robust speaker verification method using multi-stream HMMs for integrating spectral and prosodic information. The paper first shows the effectiveness obtained by using multi-stream technique in our speaker verification framework. Next, a stream-weight adaptation method using both linear discriminant analysis (LDA) and Adaboost is proposed. Experiments were conducted using four-connected-digit utterances of Japanese contaminated by white noise with various SNRs. Experimental results show that 1) the verification performance was improved in all SNR conditions by using stream weights estimated by LDA and 2) the performance is further improved by using Adaboost in 10 - 30dB SNR conditions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speaker verification / noise robustness / multi-stream HMM / stream-weight estimation / Adaboost
Paper # NLC2004-70,SP2004-110
Date of Issue

Conference Information
Committee SP
Conference Date 2004/12/14(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A stream-weight optimization method based on boosting for multi-stream speaker verification
Sub Title (in English)
Keyword(1) speaker verification
Keyword(2) noise robustness
Keyword(3) multi-stream HMM
Keyword(4) stream-weight estimation
Keyword(5) Adaboost
1st Author's Name Taichi ASAMI
1st Author's Affiliation Department of Computer Science, Tokyo Institute of Technology()
2nd Author's Name Koji IWANO
2nd Author's Affiliation Department of Computer Science, Tokyo Institute of Technology
3rd Author's Name Sadaoki FURUI
3rd Author's Affiliation Department of Computer Science, Tokyo Institute of Technology
Date 2004/12/14
Paper # NLC2004-70,SP2004-110
Volume (vol) vol.104
Number (no) 542
Page pp.pp.-
#Pages 6
Date of Issue