基于稀疏特性的欠定盲信号分离算法*

南京大学学报(自然科学版) ›› 2011, Vol. 47 ›› Issue (5): 566–570.

基于稀疏特性的欠定盲信号分离算法*

张苏弦¹，刘海林^2**

出版日期:2015-04-28 发布日期:2015-04-28
作者简介: (l.广东工业大学信息工程学院，2.广东工业大学应用数学学院，广州，510006)
基金资助:
国家自然科学基金(60974077)，广东省自然科学基金(10251009001000002)

Underdetermined blind source separation algorithm based on sparse representation

Zhann Su-Xian¹,Liu Hai一Lin²

Online:2015-04-28 Published:2015-04-28
About author: (1. Faculty of Information Engineering, 2. Faculty of Applied Mathematics Guangdong University of Technology, Guangzhou，510006，China)

摘要/Abstract

摘要： 在源信号在非充分稀疏条件卜，提出了一种改进的两步法欠定自源分离算法.与现有的大多数稀疏分量分析算法法都是假设源信号是充分稀疏不同，该算法放宽了源信号的稀疏性.与此同时，该
算法能够估计出聚类空间的个数，能够克服源信号个数未知的情况.模糊划分矩阵的应用更加有利于源信号的分离.仿真结果表明了该算法的有效性.

Abstract: Based on the insufficient sparsity assumption of the source signals，a new algorithm is presented for underdetermined blind source separation. Different with existing sparse component analysis algorithms which
assume that source signals arc strictly sparse, the proposed algorithm is able to solve sparse component analysis problem in norrstrictly condition; meanwhile, the proposed algorithm is also able to detect the clustering spaces
number when the sources number is unknown previously.The fuzzy clustering method is also helpful in the second stage. Simulations arc given to demonstrate the effectiveness of the proposed algorithm.

张苏弦¹，刘海林^2**
. 基于稀疏特性的欠定盲信号分离算法*
[J]. 南京大学学报(自然科学版), 2011, 47(5): 566–570.

Zhann Su-Xian¹,Liu Hai一Lin²
. Underdetermined blind source separation algorithm based on sparse representation
[J]. Journal of Nanjing University(Natural Sciences), 2011, 47(5): 566–570.

参考文献

[1]Georgiev P, Theis F, Cichocki A. Sparse com poncnt analysis and blind soures separation of underdetermined mixtures. IEEE Transactions of Neural Networks，2005，16 (4):992一996.
[2]He Z, Cichocki A，Li Y，et al. Khyperline clustering learning for sparse component analy sis. Signal Processing, 2009，89:1011一1022.
[3]Li YQ，Amari S, Cichocki A，et al. Probabili ty estimation for recoverability analysis of blind source separation based on sparse representa- tion. IEEE Transactions on information Theo- ry, 2006，52(7):3139一3152.
[4]Pedcrscn M S, Wang D L, Larsen J，et al. Two-microphone separation of speech mixtures. IEEE Transactions on Neural Networks, 2008 19(3):475一492.
[5]Jourjinc A，Rickard S, Yilmaz O.Blind scpara- tion of disjoint orthogonal signals:dcmixing n sources from 2 mixtures. Proceedings of IEEE Conference on Acoustics, Speech，and Signal Processing, 2000，5:2985一2988.
[6]Movahcdi N F, Hoscin M G, Babaie-Zadch M, et al. Estimating the mixing matrix in sparse component analysis(SCA) based on partial k- dimensional subspace clustering. Ncurocomput- ins, 2008，71(10):2330一2343.
[7]He Z, Cichocki A. K-EVD clustering and its applications to sparse component analysis.The 6^th International Conference on independent Component Analysis and Blind Signal Separa- tion, Charleston, USA，2006，Springcr 3889: 90一97.
[8]He Z, Cichocki A. K-subspace clustering and its application in sparse component analysis. The l4^th European Symposium on Artificial Neural Networks. Bruges, Belgium, 2006.
[9]Zhang S X，Liu H L, Wen J C,etal. A new al gorithm estimating the mixing matrix for the sparse component analysis. Proceedings of In ternational Conference on Computation lntelli gence and Security’09，2009，25一29.
[10]Bofill P Zibulevsky M Underdetermined source separation using sparse representation.Signal Processing, 2001，81:2353一2362.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed