Presentation 2003/5/23
Speaker Identification by Combining Speaker Specific GMM with Speaker Adapted Syllable-based HMM
Seiichi NAKAGAWA, Wei ZHANG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We present a new text-independent speaker recognition method by combining speaker-specific Gaussian Mixture Model (GMM) with syllable-based HMM adapted by MLLR or MAP. The robustness of this speaker recognition method for speaking style's change was evaluated. The speaker identification experiment using NTT database which consists of sentences uttered at three speed modes (normal, fast and slow) by 35 Japanese speakers (22 males and 13 females) on five sessions over ten months was conducted. Each speaker uttered only 5 training utterances. We obtained the accuracy of 100% for text-independent speaker identification. This result was superior to some conventional methods for the same database.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speaker identification / GMM / Speaker adaptation / HMM
Paper # SP2003-31
Date of Issue

Conference Information
Committee SP
Conference Date 2003/5/23(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) Speaker Identification by Combining Speaker Specific GMM with Speaker Adapted Syllable-based HMM
Sub Title (in English)
Keyword(1) Speaker identification
Keyword(2) GMM
Keyword(3) Speaker adaptation
Keyword(4) HMM
1st Author's Name Seiichi NAKAGAWA
1st Author's Affiliation Departmento of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Wei ZHANG
2nd Author's Affiliation Departmento of Information and Computer Sciences, Toyohashi University of Technology
Date 2003/5/23
Paper # SP2003-31
Volume (vol) vol.103
Number (no) 94
Page pp.pp.-
#Pages 6
Date of Issue