Presentation 1999/8/5
A sound source segregation method using the harmonic structure of the human voice
Masaharu Sakamoto, Michio Yamada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a sound segregation method that can segregate speech sounds from a variety of interference sound. First, a time-frequency representation of mixed sounds is derived from a Gabor wavelet transform. Next, subgroups of time-frequency elements are formed according to several acoustical features of the time-frequency representation. Finally, a search strategy is used to group the subgroups according to Bregman's concept of auditory scene analysis. We conducted a segregation experiment, using a mixture of male and female voices.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sound segregation / Gabor wavelet / wavelet transform / auditory scene analysis
Paper # SP99-56
Date of Issue

Conference Information
Committee SP
Conference Date 1999/8/5(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 sound source segregation method using the harmonic structure of the human voice
Sub Title (in English)
Keyword(1) sound segregation
Keyword(2) Gabor wavelet
Keyword(3) wavelet transform
Keyword(4) auditory scene analysis
1st Author's Name Masaharu Sakamoto
1st Author's Affiliation Graduate School of Mathematical Sciences, University of Tokyo:(Tokyo Research Laboratory, IBM Japan)()
2nd Author's Name Michio Yamada
2nd Author's Affiliation Graduate School of Mathematical Sciences,University of Tokyo
Date 1999/8/5
Paper # SP99-56
Volume (vol) vol.99
Number (no) 255
Page pp.pp.-
#Pages 8
Date of Issue