Convolutive blind source separation method based on tensor decomposition

被引：0

作者：

Ma B. ^{[1
]}

Zhang T. ^{[1
]}

An Z. ^{[1
]}

Deng P. ^{[1
]}

机构：

[1] Chongqing Key Laboratory of Signal and Information Processing, School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing

来源：

Tongxin Xuebao/Journal on Communications | 2021年 / 42卷 / 08期

基金：

中国国家自然科学基金;

关键词：

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

D O I：

10.11959/j.issn.1000-436x.2021140

中图分类号：

学科分类号：

摘要：

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. © 2021, Editorial Board of Journal on Communications. All right reserved.

引用

页码：52 / 60

页数：8

共 14 条

[1] ZHANG T Q, MA B Z, QIANG X Z, Et al., Variable-step blind source separation method with adaptive momentum factor, Journal on Communications, 38, 3, pp. 16-24, (2017)
[2] MAZUR R, MERTINS A., An approach for solving the permutation problem of convolutive blind source separation based on statistical signal models, IEEE Transactions on Audio, Speech, and Language Processing, 17, 1, pp. 117-126, (2009)
[3] XIE K, ZHOU G X, YANG J J, Et al., Eliminating the permutation ambiguity of convolutive blind source separation by using coupled frequency bins, IEEE Transactions on Neural Networks and Learning Systems, 31, 2, pp. 589-599, (2020)
[4] KANG F, YANG F R, YANG J., A low-complexity permutation alignment method for frequency-domain blind source separation, Speech Communication, 115, pp. 88-94, (2019)
[5] KEMIHA M, KACHA A., Complex blind source separation, Circuits, Systems, and Signal Processing, 36, 11, pp. 4670-4687, (2017)
[6] LEE I, KIM T, LEE T W., Fast fixed-point independent vector analysis algorithms for convolutive blind source separation, Signal Processing, 87, 8, pp. 1859-1871, (2007)
[7] KITAMURA D, ONO N, SAWADA H, Et al., Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 24, 9, pp. 1626-1641, (2016)
[8] FU X, IBRAHIM S, WAI H T, Et al., Block-randomized stochastic proximal gradient for low-rank tensor factorization, IEEE Transactions on Signal Processing, 68, pp. 2170-2185, (2020)
[9] LATHAUWER L D, MOOR B D, VANDEWALLE J., Computation of the canonical decomposition by means of a simultaneous generalized schur decompo-sition, SIAM Journal on Matrix Analysis and Applications, 26, 2, pp. 295-327, (2004)
[10] YEREDOR A., Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation, IEEE Transactions on Signal Processing, 50, 7, pp. 1545-1553, (2002)

← 1 2 →