Frequency Domain Blind Source Separation Permutation Algorithm Based on Regional Growth Correction

被引：0

作者：

Zhang T. ^{[1
]}

Zhang H. ^{[1
]}

Liu D. ^{[1
]}

Li Q. ^{[1
]}

机构：

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

来源：

Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | 2019年 / 41卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Convolutive blind source separation; Frequency domain permutation; Power ratio correlation; Region growing;

D O I：

10.11999/JEITdzyxxxb-41-3-580

中图分类号：

学科分类号：

摘要：

The convolutive blind source separation can be effectively solved in frequency domain, but blind source separation in frequency domain must solve the problem of ranking ambiguity. A frequency-domain blind source separation sorting algorithm is proposed based on regional growth correction. First, the convolutional mixed signal short-time Fourier transform is used to establish an instantaneous model at each frequency point in the frequency domain for independent component analysis. Based on this, the correlation of the power ratio of the separated signal is used to sort all frequency points one by one replacement. Second, according to the threshold, the sorted result is divided into several small areas. Finally. regional replacement and merging is performed according to the regional growth method, and the correct separation signal is finally obtained. Regional growth correction minimizes the mis-proliferation of frequency sorting and improves separation results. The speech blind source separation experiments are performed in the simulated and real environments respectively. The results show the effectiveness of the proposed algorithm. © 2019, Science Press. All right reserved.

引用

页码：580 / 587

页数：7

共 14 条

[1]

Zhang T., Ma B., Qiang X., Et al., Variable-step blind source separation algorithm with adaptive momentum item for chaotic signals, Journal of Electronics & Information Technology, 39, 4, pp. 908-914, (2017)

[2]

Ou S., Geng C., Gao Y., Momentum term based blind source separation algorithm and its performance modified strategies, Acta Electronica Sinica, 42, 1, pp. 42-48, (2014)

[3]

Xu C., Hao Y., Lu L., Et al., Fast angle estimation algorithm based on cross-correlation, Journal of Electronics & Information Technology, 38, 6, pp. 1446-1451, (2016)

[4]

Hu K., Wang Z., A time-frequency analysis based blind source deconvolution method, Acta Electronica Sinica, 34, 7, pp. 1246-1254, (2006)

[5]

Yoshioka T., Nakatani T., Miyoshi M., Et al., Blind separation and dereverberation of speech mixtures by joint optimization, IEEE Transactions on Audio, Speech and Language Processing, 19, 1, pp. 69-84, (2011)

[6]

Ou X., Zhang T., Yan Z., Et al., Blind convolution speech separation based on multi-band ordering, Application Research of Computers, 33, 5, pp. 1481-1485, (2016)

[7]

Parra L., Spence C., Convolutive blind separation of non-stationary sources, IEEE Transactions on Speech Audio Process, 8, 3, pp. 320-327, (2000)

[8]

Ikram M., Morgan D., Permutation inconsistency in blind speech separation: Investigation and solutions, IEEE Transactions on Speech & Audio Process, 13, 1, pp. 1-13, (2005)

[9]

Zhang H., Feng D., Pang J., A time-domain blind convolutive separation algorithm for speech signals based on second-order statistic, Journal of Electronics & Information Technology, 32, 5, pp. 1083-1086, (2010)

[10]

Sawada H., Mukai R., Araki S., Et al., A robust and precise method for solving the permutation problem of frequency domain blind source separation, IEEE Transactions on Speech Audio Process, 12, 5, pp. 530-538, (2004)

← 1 2 →