|Table of Contents|

Frequency-domain blind separation of convolutive mixtures based on Parseval's theorem


Research Field:
Publishing date:


Frequency-domain blind separation of convolutive mixtures based on Parseval's theorem
Yang Qingchuan1Zang Chuanxia1Li Tianlei2Hu Yulan1Mei Tiemin1
1.School of Information Science and Engineering,Shenyang Ligong University,Shenyang 110168,China; 2.AVIC Shenyang Aircraft Engine Design Institute,Shenyang 110015,China
convolutive mixing blind source separation double-least-mean-squeres Parseval's theorem frequency-integration algorithm fast Fourier transform
To improve the performance of the blind source separation double least mean squeres(Double-LMS)algorithm which is computationally inefficient if the separation filters are too long,the Double-LMS is converted to a frequency-integration algorithm with the help of Parseval's theorem.Fast Fourier transform is exploited to implement the proposed algorithm to overcome the low computational efficiency problem due to the too long separation filters.Simulations show that the new algorithm works as well as the Double-LMS algorithm and has higher computation efficiency.


[1] 付卫红,杨小牛,曾兴雯,等.适用于通信侦察的信号盲分离算法[J].南京理工大学学报,2008,32(2):189-194.
Fu Weihong,Yang Xiaoniu,Zeng Xingwen,et al.Signal blind separation algorithm applying to communication reconnaissance[J].Journal of Nanjing University of Science and Technology,2008,32(2):189-194.
[2]Amari S,Cichocki A.Adaptive blind signal processing-neural network approaches[J].Proceedings of the IEEE,1998,86(10):2026-2048.
[3]Comon P.Independent component analysis,a new concept?[J].Signal Processing,1994,36(3):287-314.
[4]Hyvärinen A.Fast and robust fixed-point algorithms for independent component analysis[J].IEEE Transactions on Neural Networks,1999,10(3):626-634.
[5]Belouchrani A,Abed-Meraim K,Cardoso J F,et al.A blind source separation technique using second-order statistics[J].IEEE Transactions on Signal Processing,1997,45(2):434-443.
[6]Tong L,Liu R,Soon V C,et al.Indeterminacy and identifiability of blind identification[J].IEEE Transactions on Circuits and Systems,1991,38(5):499-509.
[7]Mei T,Mertins A,Yin F.On the generalization of blind source separation algorithms from instantaneous to convolutive mixtures[A].IEEE Proceedings of Sensor Array and Multichannel Signal Processing Workshop[C].Shanghai,China:IEEE Computer Society,2008:482-486.
[8]Kawamoto M,Matsuoka K,Ohnishi N.A method of blind separation for convolved non-stationary signals[J].Neurocomputing,1998,22(1-3):157-171.
[9]Almeida M S C,Almeida L B.Nonlinear separation of show-through image mixtures using a physical model trained with ICA[J].Signal Processing,2012,92(4):872-884.
[10]Parra L,Spence C.Convotulive blind separation of non-stationary sources[J].IEEE Transactions on Speech and Audio Processing,2000,8(3):320-327.
[11]Smaragdis P.Blind separation of convolved mixtures in the frequency domain[J].Neurocomputing,1998,22(1-3):21-34.
[12]Mei T,Yin F.Blind separation of convolutive mixtures by decorrelation[J].Signal Processing,2004,84(12):2297-2313.
[13]Mei T,Xi J,Yin F,et al.Blind source separation based on time-domain optimization of a frequency-domain independence criterion[J].IEEE Transactions on Audio,Speech and Language Processing,2006,14(6):2075-2085.
[14]Yin F,Mei T,Wang J.Blind-source separation based on decorrelation and nonstationarity[J].IEEE Transactions on Circuits and Systems I:Regular Papers,2007,54(5):1150-1158.
[16]Mei T,Yin F,Wang J.Blind source separation based on cumulants with time and frequency non-properties[J].IEEE Transactions on Audio,Speech,and Language Processing,2009,17(6):1099-1108.
[17]Ahmad R,Khong A W H,Hasan M K,et al.An extended normalized multichannel FLMS algorithm for blind channel identification[A].Proceedings of European Signal Processing Conference[C].Florence,Italy:Eurasip,2006.
[18]Allen J B,Berkley D A.Image method for efficiently simulating small-room acoustics[J].Journal of the Acoustical Society of America,1979,65(4):943-950.


Last Update: 2015-02-28