Blind source separation of mixed speech in a high reverberation environment

Keiju Iso, Shoko Araki, Shoji Makino, Tomohiro Nakatani, Hiroshi Sawada, Takeshi Yamada, Atsushi Nakamura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Blind source separation (BSS) is a technique for estimating and separating individual source signals from a mixed signal using only information observed by each sensor. BSS is still being developed for mixed signals that are affected by reverberation. In this paper, we propose combining the BSS method that considers reverberation proposed by Duong et al. with the BSS method reported by Sawada et al., which does not consider reverberation, for the initial setting of the EM algorithm. This proposed method assumes the underdetermined case. In the experiment, we compare the proposed method with the conventional method reported by Duong et al. and that reported by Sawada et al., and demonstrate the effectiveness of the proposed method.

Original languageEnglish
Title of host publication2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11
Pages36-39
Number of pages4
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11 - Edinburgh, United Kingdom
Duration: 2011 May 302011 Jun 1

Publication series

Name2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11

Other

Other2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11
CountryUnited Kingdom
CityEdinburgh
Period11/5/3011/6/1

Keywords

  • blind source separation
  • model parameter estimation
  • reverberation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Communication

Fingerprint Dive into the research topics of 'Blind source separation of mixed speech in a high reverberation environment'. Together they form a unique fingerprint.

Cite this