Convolutive blind source separation method based on tensor decomposition

Baoze Ma, Tianqi Zhang, Zeliang An, Pan Deng

Research output: Contribution to journalJournal articleResearchpeer-review

4 Citations (Scopus)

Abstract

A convolutive blind source separation algorithm was proposed based on tensor decomposition framework, to address the estimation of mixed filter matrix and the permutation alignment of frequency bin simultaneously. Firstly, the tensor models at all frequency bins were constructed according to the estimated autocorrelation matrix of the observed signals. Secondly, the factor matrix corresponding to each frequency bin was calculated by tensor decomposition technique as the estimated mixed filter matrix for that bin. Finally, a global optimal permutation strategy with power ratio as the permutation alignment measure was adopted to eliminate the permutation ambiguity in all the frequency bins. Experimental results demonstrate that the proposed method achieves better separation performance than other existing algorithms when dealing with convolutive mixed speech under different simulation conditions.
Original languageEnglish
JournalTongxin Xuebao/Journal on Communications
Volume42
Issue number8
Pages (from-to)52-60
Number of pages9
ISSN1000-436X
DOIs
Publication statusPublished - 25 Aug 2021
Externally publishedYes

Keywords

  • Autocorrelation matrix
  • Convolutive blind source separation
  • Permutation ambiguity
  • Tensor decomposition

Fingerprint

Dive into the research topics of 'Convolutive blind source separation method based on tensor decomposition'. Together they form a unique fingerprint.

Cite this