Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors

Shoko Araki, Hiroshi Sawada, Ryo Mukai, Shoji Makino

Research output: Contribution to journalArticlepeer-review

206 Citations (Scopus)

Abstract

This paper presents a new method for blind sparse source separation. Some sparse source separation methods, which rely on source sparseness and an anechoic mixing model, have already been proposed. These methods utilize level ratios and phase differences between sensor observations as their features, and they separate signals by classifying them. However, some of the features cannot form clusters with a well-known clustering algorithm, e.g., the k-means. Moreover, most previous methods utilize a linear sensor array (or only two sensors), and therefore they cannot separate symmetrically positioned sources. To overcome such problems, we propose a new feature that can be clustered by the k-means algorithm and that can be easily applied to more than three sensors arranged non-linearly. We have obtained promising results for two- and three-dimensionally distributed speech separation with non-linear/non-uniform sensor arrays in a real room even in underdetermined situations. We also investigate the way in which the performance of such methods is affected by room reverberation, which may cause the sparseness and anechoic assumptions to collapse.

Original languageEnglish
Pages (from-to)1833-1847
Number of pages15
JournalSignal Processing
Volume87
Issue number8
DOIs
Publication statusPublished - 2007 Aug
Externally publishedYes

Keywords

  • Binary mask
  • Blind source separation
  • Clustering
  • Normalization
  • Reverberation
  • Sparseness
  • Speech separation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors'. Together they form a unique fingerprint.

Cite this