Presentation 1996/3/8
Multiple Speech Segregation by Using the Optimum Harmonics Tracking Filter
Kazuki Nishi, Mototsugu Abe, Shigeru Ando,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new harmonics tracking algorithm for auditory scene analysis. It extracts the most significant stream from multiple sound streams as well as the tracking of each harmonic components. For the optimum tracking of pitch candidates, a novel estimation technique based on nonlinear Kalman filtering and Parzen estimate (non-parametric Kalman filter, NPKF) is used. For invariant reconstruction of harmonic components against pitch estimation error, we perform filtering process in the wavelet domain. Using simulated data and real world data, we show several experimental results for extracting the most dominant sound stream among multiple ones.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Auditory Scene Analysis / Harmonics Tracking / Wavelet Analysis / Pitch Estimation
Paper # SP95-148
Date of Issue

Conference Information
Committee SP
Conference Date 1996/3/8(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) Multiple Speech Segregation by Using the Optimum Harmonics Tracking Filter
Sub Title (in English)
Keyword(1) Auditory Scene Analysis
Keyword(2) Harmonics Tracking
Keyword(3) Wavelet Analysis
Keyword(4) Pitch Estimation
1st Author's Name Kazuki Nishi
1st Author's Affiliation University of Electro-Communications()
2nd Author's Name Mototsugu Abe
2nd Author's Affiliation The University of Tokyo
3rd Author's Name Shigeru Ando
3rd Author's Affiliation The University of Tokyo
Date 1996/3/8
Paper # SP95-148
Volume (vol) vol.95
Number (no) 566
Page pp.pp.-
#Pages 8
Date of Issue