Blind source separation of convolutive mixtures of speech in frequency domain

Shoji Makino*, Hiroshi Sawada, Ryo Mukai, Shoko Araki

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

53 Citations (Scopus)

Abstract

This paper overviews a total solution for frequency-domain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2 × 2, 3 × 3, 4 × 4, 6 × 8, and 2 × 2 (moving sources), (#sources × #microphones) in a room are promising.

Original languageEnglish
Pages (from-to)1640-1654
Number of pages15
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE88-A
Issue number7
DOIs
Publication statusPublished - 2005 Jul
Externally publishedYes

Keywords

  • Adaptive beamformer
  • Blind source separation
  • Convolutive mixtures
  • Frequency-domain BSS
  • Independent component analysis
  • Microphone array

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Blind source separation of convolutive mixtures of speech in frequency domain'. Together they form a unique fingerprint.

Cite this