Bayesian extension of MUSIC for sound source localization and tracking

Takuma Otsuka; Kazuhiro Nakadai; Tetsuya Ogata; Hiroshi G. Okuno

Bayesian extension of MUSIC for sound source localization and tracking

Takuma Otsuka^*, Kazuhiro Nakadai, Tetsuya Ogata, Hiroshi G. Okuno

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

9 Citations (Scopus)

Abstract

This paper presents a Bayesian extension of MUSIC-based sound source localization (SSL) and tracking method. SSL is important for distant speech enhancement and simultaneous speech separation for improving speech recognition, as well as for auditory scene analysis by mobile robots. One of the draw- backs of existing SSL methods is the necessity of careful param- eter tunings, e.g., the sound source detection threshold depend- ing on the reverberation time and the number of sources. Our contribution consists of (1) automatic parameter estimation in the variational Bayesian framework and (2) tracking of sound sources with reliability. Experimental results demonstrate our method robustly tracks multiple sound sources in a reverberant environment with RT20 = 840 (ms).

Original language	English
Pages (from-to)	3109-3112
Number of pages	4
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication status	Published - 2011 Dec 1
Externally published	Yes
Event	12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy Duration: 2011 Aug 27 → 2011 Aug 31

Keywords

MUSIC algorithm
Particle filter
Simultaneous sound source localization
Variational Bayes

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

@article{41882f39848b43c880cd9183440f5047,

title = "Bayesian extension of MUSIC for sound source localization and tracking",

abstract = "This paper presents a Bayesian extension of MUSIC-based sound source localization (SSL) and tracking method. SSL is important for distant speech enhancement and simultaneous speech separation for improving speech recognition, as well as for auditory scene analysis by mobile robots. One of the draw- backs of existing SSL methods is the necessity of careful param- eter tunings, e.g., the sound source detection threshold depend- ing on the reverberation time and the number of sources. Our contribution consists of (1) automatic parameter estimation in the variational Bayesian framework and (2) tracking of sound sources with reliability. Experimental results demonstrate our method robustly tracks multiple sound sources in a reverberant environment with RT20 = 840 (ms).",

keywords = "MUSIC algorithm, Particle filter, Simultaneous sound source localization, Variational Bayes",

author = "Takuma Otsuka and Kazuhiro Nakadai and Tetsuya Ogata and Okuno, {Hiroshi G.}",

year = "2011",

month = dec,

day = "1",

language = "English",

pages = "3109--3112",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

note = "12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 ; Conference date: 27-08-2011 Through 31-08-2011",

}

TY - JOUR

T1 - Bayesian extension of MUSIC for sound source localization and tracking

AU - Otsuka, Takuma

AU - Nakadai, Kazuhiro

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper presents a Bayesian extension of MUSIC-based sound source localization (SSL) and tracking method. SSL is important for distant speech enhancement and simultaneous speech separation for improving speech recognition, as well as for auditory scene analysis by mobile robots. One of the draw- backs of existing SSL methods is the necessity of careful param- eter tunings, e.g., the sound source detection threshold depend- ing on the reverberation time and the number of sources. Our contribution consists of (1) automatic parameter estimation in the variational Bayesian framework and (2) tracking of sound sources with reliability. Experimental results demonstrate our method robustly tracks multiple sound sources in a reverberant environment with RT20 = 840 (ms).

AB - This paper presents a Bayesian extension of MUSIC-based sound source localization (SSL) and tracking method. SSL is important for distant speech enhancement and simultaneous speech separation for improving speech recognition, as well as for auditory scene analysis by mobile robots. One of the draw- backs of existing SSL methods is the necessity of careful param- eter tunings, e.g., the sound source detection threshold depend- ing on the reverberation time and the number of sources. Our contribution consists of (1) automatic parameter estimation in the variational Bayesian framework and (2) tracking of sound sources with reliability. Experimental results demonstrate our method robustly tracks multiple sound sources in a reverberant environment with RT20 = 840 (ms).

KW - MUSIC algorithm

KW - Particle filter

KW - Simultaneous sound source localization

KW - Variational Bayes

UR - http://www.scopus.com/inward/record.url?scp=84865790519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865790519&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84865790519

SN - 2308-457X

SP - 3109

EP - 3112

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011

Y2 - 27 August 2011 through 31 August 2011

ER -

Bayesian extension of MUSIC for sound source localization and tracking

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this