一种非平稳卷积混合信号的时域盲源分离算法

徐舜; 刘郁林; 陈绍荣

doi:10.3724/SP.J.1146.2006.01273

一种非平稳卷积混合信号的时域盲源分离算法

doi: 10.3724/SP.J.1146.2006.01273

基金项目:

国家自然科学基金(60672157，60672158)资助课题

计量
- 文章访问数: 3219
- HTML全文浏览量: 80
- PDF下载量: 931
- 被引次数: 0
出版历程
- 收稿日期: 2006-08-28
- 修回日期: 2007-01-30
- 刊出日期: 2008-03-19

A Time-Domain Algorithm for Blind Source Separation of Non-stationary Convolutive Mixtures

摘要

摘要: 该文将卷积混合盲源分离模型中的向量进行重新规划并对联合近似对角化方法加以推广，提出一种非平稳卷积混合信号的时域盲源分离算法。该算法先将采集到的卷积混合信号进行重排，使之满足重新定义向量后的瞬时混合模型特征，然后考虑到信号的非平稳特性，采用空间白化和联合近似块对角化方法分离出源信号。由于没有使用域变换而是从新的角度将卷积混合问题简化为瞬时混合问题，避免了卷积运算或域映射过程，降低了算法的复杂度。仿真实验验证了该算法的有效性并就参数的变化对信号干扰比的影响进行了分析。
- 盲源分离; 非平稳卷积混合信号; 联合块对角化; 白化
Abstract: In this paper, a time-domain blind source separation algorithm for non-stationary convolutive mixtures is proposed by reprogramming the vectors of convolutive mixture model and generalizing the joint approximate diagonalization method. Firstly the sampling convolutive mixture signals are reseted for matching instantaneous mixture model, then considering non-stationarity of the sources, space whitening and joint block-diagonalization method is exploited to obtain the original signals. This algorithm simplifies the convolutive mixture problem into the instantaneous mixture problem from a new point of view, so it avoids domain transformation and convolution operation, as well as decreases the complexity. Computer simulation verifies its effectiveness and gives the analysis results about the effect on the signal to interference ratio as its parameter changes.

HTML全文

参考文献(1)

Cichocki A and Amari S. Adaptive Blind Signal and ImageProcessing: Learning Algorithm and Appilication [M].England: John Wiley, 2002, Chapter 1.[2]Crucez-Alvarez S A, Cichocki A, and Amari S. From blindsignal extraction to blind instantaneous signal separation:criteria, algorithms and stability[J]. IEEE Trans. on NeuralNetworks, 2004, 15(4): 859-873.[3]Makino S, Sawada H. Mukai R, and Araki S, Blind sourceseparation of convolutive mixtures of speech in frequencydomain[J].IEICE Trans. Fundamentals.2005, E88-A(7):1640-1655[4]Araki S, Mukai R, Makino S, Nishikawa T, and SaruwatariH. The fundamental limitation of frequency domain blindsource separation for convolutive mixtures of speech[J].IEEETrans. on Speech Audio Processing.2003, 11(2):109-116[5]Georgiev P G, Theis F, and Cichocki A. Sparse componentanalysis and blind source separation of underdeterminedmixtures[J].IEEE Trans. on Neural Networks.2005, 16(4):992-996[6]赵彩华, 刘琚, 孙建德, 闫华. 基于小波变换和独立分量分析的含噪混叠语音盲分离[J].电子与信息学报.2006, 28(9):1565-1568浏览[7]Cardoso J F. Multidimensional independent componentanalysis[A]. In Proc. ICASSP, Seattle, 1998: 1941-1944.[8]Choi S, Cichocki A, Park H M, and Lee S Y. Blind sourceseparation and independent component analysis: A review[J].Neural Information Processing-Letters and Reviews, 2005,6(1): 1-57.[9]Cichicki A and Unbehauen R. Neural Networks forOptimization and Signal Processing[M]. John Wiley Sons,New York, 1994, chapter 5.

施引文献

资源附件(0)

访问统计