Presentation 2004/12/15
Constructing a Family Tree of Multilingual Speech Based on Gaussian Mixture Models
Shiwei ZHU, Mikio YAMAMOTO, Shuichi ITAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a method for automatically clustering multilingual speech. We consider that language is the source of information which generates the speech feature parameter, and the probability and the statistical characteristics of these information are modeled by GMMs. Next, a distance measure between GMMs is proposed. Based on this we construct a family tree of multilingual speech.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Gaussian Mixture Model / Family Tree of Multilanguage Speeches / Clustering
Paper # NLC2004-93,SP2004-133
Date of Issue

Conference Information
Committee NLC
Conference Date 2004/12/15(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Constructing a Family Tree of Multilingual Speech Based on Gaussian Mixture Models
Sub Title (in English)
Keyword(1) Gaussian Mixture Model
Keyword(2) Family Tree of Multilanguage Speeches
Keyword(3) Clustering
1st Author's Name Shiwei ZHU
1st Author's Affiliation Master's Program in Science and Engineering, University of Tsukuba()
2nd Author's Name Mikio YAMAMOTO
2nd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba
3rd Author's Name Shuichi ITAHASHI
3rd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba
Date 2004/12/15
Paper # NLC2004-93,SP2004-133
Volume (vol) vol.104
Number (no) 540
Page pp.pp.-
#Pages 5
Date of Issue