时域卷积信号的交替最小二乘盲分离算法

张华; 冯大政; 庞继勇

doi:10.3724/SP.J.1146.2009.00927

时域卷积信号的交替最小二乘盲分离算法

doi: 10.3724/SP.J.1146.2009.00927

张华^{① 冯大政,},
冯大政,
庞继勇

基金项目:

国家自然科学基金(60672128，60702057)资助课题

计量
- 文章访问数: 3764
- HTML全文浏览量: 99
- PDF下载量: 899
- 被引次数: 0
出版历程
- 收稿日期: 2009-06-26
- 修回日期: 2010-05-24
- 刊出日期: 2010-10-19

Time-domain Convolutive Blind Separation Based on Alternative Least-squares

Zhang Hua^{① 冯大政
,},
Feng Da-Zheng,
Pang Ji-Yong

摘要

摘要: 该文分析时域卷积接收信号的时延相关矩阵具有的可联合块对角化的三因子乘积结构，通过对其所构成的3维矩阵进行切片分割和重新排列规划，提出基于交替最小二乘的三因子迭代计算方法，实现非正交联合块对角化，直接在时域解决卷积盲分离问题。实验仿真表明，与传统的联合块对角化算法相比，所提算法的收敛性能更好且更稳定，并且不受限于初始参数的选择；分离信号的相异度指标和巴克谱失真测度分别改善达到4.35 dB和0.22。
- 信号处理 /
- 卷积盲分离 /
- 交替最小二乘 /
- 联合块对角化
Abstract: Temporal correlation matrices of the convolutive-mixture signals possess the struture of tri-factor multiplication and so can be jointly diagonalized blockwise. Though cutting to pieces and then reprogramming of the 3-D matrix composed of a group of correlation matrices, an alternating and iterative approach is proposed to achieve the least-squares solutions and then to estimate the channel mixture matirx for realizing convolutive blind separation in time domain. Compared with traditional joint block-diagonalization algorithms, simulation results show that the proposed one has better and more stable separation performance irrespective of initial parameters. The dissimilarity index and Bark sepectral distortion are improved by 4.35 dB and 0.22 respectively.
- Signal processing /
- Convolutive blind source separation /
- Alternative least squares /
- Joint block-diagonalization

HTML全文

参考文献(1)

刘建强, 冯大政. 基于多信道信号增强的卷积混叠语音信号盲分离的后处理方法[J]. 电子学报, 2007, 35(2): 2389-2393.Liu Jian-qiang and Feng Da-zheng. Blind separation of convolutive speech mixtures with post-processing based on multichannel signal enhancement[J]. Acta Electronia Sinica, 2007, 35(2): 2389-2393.[2]王睿, 方勇. 基于2-D共因子的精确提取的图像盲复原方法[J].电子与信息学报.2009, 31(1):108-111浏览Wang Rui and Fang Yong. Blind restoration of blurred image based on precise extraction of 2-D GCD[J].Journal of Electronics Information Technology.2009, 31(1):108-111[3]付卫红, 杨小牛, 刘乃安, 曾兴雯. 基于子空间分解的多通道盲解卷积算法[J]. 电子与信息学报, 2009, 30(1): 25-30.Fu Wei-hong, Yang Xiao-niu, Liu Nai-an, and Zeng Xing-wen. Algorithm for multichannel blind deconvolution based on subspace decomposition[J].Journal of Electronics Information Technology.2009, 30(1):25-30[4]Abed-Meraim K and Beloucharni A. Algorithms for joint block diagonalization[C]. Proc. EUSIPCO04, Vienna, Austria, Sept. 6-10, 2004: 209-212.[5]Ghennioui H, Fadaili E M, and Moreau N T, et al.. A nonunitary joint block diagonalization algorithm for blind separation of convolutive mixtures of sources[J].IEEE Signal Processing Letters.2007, 14(11):860-863[6]Fadaili E M, Thirion-Moreau N, and Moreau E. Non-orthogonal joint diagonalization/zeros-diagonalization for source separation based on time-frequency distributions[J].IEEE Transactions on Signal Processing.2007, 55(5):1673-1687[7]易克初, 田斌, 付强. 语音信号处理[M]. 北京：国防工业出版社, 2001: 146-147.

施引文献

资源附件(0)

访问统计