論文

査読有り
2017年

BAYESIAN MULTICHANNEL NONNEGATIVE MATRIX FACTORIZATION FOR AUDIO SOURCE SEPARATION AND LOCALIZATION

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
  • Kousuke Itakura
  • ,
  • Yoshiaki Bando
  • ,
  • Eita Nakamura
  • ,
  • Katsutoshi Itoyama
  • ,
  • Kazuyoshi Yoshii
  • ,
  • Tatsuya Kawahara

開始ページ
551
終了ページ
555
記述言語
英語
掲載種別
研究論文(国際会議プロシーディングス)
DOI
10.1109/ICASSP.2017.7952216
出版者・発行元
IEEE

This paper presents a Bayesian extension of multichannel nonnegative matrix factorization (MNMF) that decomposes the complex spectrograms of mixture signals recorded by a microphone array into basis spectra, their temporal activations, and the spatial correlation matrices of sources (directions) in the time-frequency-channel domain. Although the original MNMF can be used in a blind setting, prior knowledge of a microphone array is useful for improving source separation. The impulse response (spatial correlation matrix) of each direction can be measured in an anechoic room, however, it differs from that in a real environment where the microphone array is used. To solve this, we propose a unified Bayesian model of source separation and localization by introducing a prior distribution determined by an anechoic spatial correlation matrix on areal spatial correlation matrix with respect to each direction. This enables us to adaptively estimate areal spatial correlation matrix and the direction of each source. Experimental results showed that our method outperformed the original MNMF and the state-of-the-art methods with prior knowledge in terms of signal-to-distortion ratio (SDR) even when the method was used in an unknown environment with acoustic characteristics different from those of the anechoic room.

リンク情報
DOI
https://doi.org/10.1109/ICASSP.2017.7952216
DBLP
https://dblp.uni-trier.de/rec/conf/icassp/ItakuraBNIYK17
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000414286200111&DestApp=WOS_CPL
URL
http://dblp.uni-trier.de/db/conf/icassp/icassp2017.html#conf/icassp/ItakuraBNIYK17
ID情報
  • DOI : 10.1109/ICASSP.2017.7952216
  • ISSN : 1520-6149
  • DBLP ID : conf/icassp/ItakuraBNIYK17
  • Web of Science ID : WOS:000414286200111

エクスポート
BibTeX RIS