Presentation 2012-03-09
Tracking of multiple moving sound sources using particle filter for arbitrary array configuration
Ai KIJIMA, Yusuke HIOKA, Nozomu HAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Studies on the direction of arrival estimation of sound sources using a microphone array have been interested. In real circumstances relative locations between sensors and sources are not always stationary. This study proposes the method to track moving sources based on a recently developed method employing the time-frequency analysis. Specific feature of the moving sources problem is to obtain accurate estimate utilizing the observation within a short time interval, thus stable estimation will be difficult. A particle filter approach with introduced particle groups corresponding individual sources is proposed in this study which enables to track the moving sound source by using short period of time-frequency data. The method alters the number of particle groups dynamically and it can track multiple sources direction simultaneously. Through the conducted experiments, the method was proved to be effective even for real environments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) particle filter / moving sound sources / time-frequency analysis / delay histogram
Paper # CAS2011-155,SIP2011-175,CS2011-147
Date of Issue

Conference Information
Committee CAS
Conference Date 2012/3/1(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 Circuits and Systems (CAS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Tracking of multiple moving sound sources using particle filter for arbitrary array configuration
Sub Title (in English)
Keyword(1) particle filter
Keyword(2) moving sound sources
Keyword(3) time-frequency analysis
Keyword(4) delay histogram
1st Author's Name Ai KIJIMA
1st Author's Affiliation Department of System Design Engineering, Faculty of Science and Technology, Keio University()
2nd Author's Name Yusuke HIOKA
2nd Author's Affiliation NTT Cyber Space Laboratories, NTT corporation
3rd Author's Name Nozomu HAMADA
3rd Author's Affiliation Department of System Design Engineering, Faculty of Science and Technology, Keio University
Date 2012-03-09
Paper # CAS2011-155,SIP2011-175,CS2011-147
Volume (vol) vol.111
Number (no) 465
Page pp.pp.-
#Pages 6
Date of Issue