Abstract
This paper proposes a method of blind separation which extracts independent signals from their convolutive mixtures. The function is acquired by modifying a network’s parameters so that a cost function takes the minimum at anytime. Firstly we propose a regulation of a nonlinear principle component analysis (PCA) cost function for blind source separation of convolutive mixtures. Then by minimizing the cost function a new recursive least-squares (RLS) algorithm is developed in time domain, and we proposed two update equations for recursively computing the regularized factor. This algorithm has two stages: one is pre-whitening, the other is RLS iteration. Simulations show that our algorithm can successfully separate convolutive mixtures and has fast convergence rate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Amari, S., Douglas, S.C., Cichocki, A., Yang, H.H.: Multi-channel blind deconvolution and equalization using the natural gradient. In: Proc. IEEE Workshop on Signal Processing Advances in Wireless Communication, Paris, France, April 1997, pp. 101–104. IEEE Computer Society Press, Los Alamitos (1997)
Comon, P.: Independent component analysis, A new concept? Signal Processing 36(3), 287–314 (1994)
Dapena, A., Castedo, L.: A novel frequency domain approach for mixtures of temporally-white signals. Digital Signal Processing 13(2), 301–316 (2003)
Dapena, A., Servitere, C., Castedo, L.: Inversion of the sliding Fourier transform using only two frequency bins and its application to source separation. Signal Processing 83(2), 453–457 (2003)
Ma, L.Y., Li, H.W.: An algorithm based on nonlinear PCA for blind separation of convolutive mixtures. Acta Electronica Sinica (Chinese) (submitted)
Matsuoka, K., Nakashima, S.: A robust algorithm for independent component analysis. In: SICE Annual Conference, Fukui, Japan, August 2003, pp. 2131–2136 (2003)
Murata, N., Ikeda, S., Ziehe, A.: An approach to blind source separation based on temporal structure of speech signals. Neurocomputing 41(1-4), 1–24 (2001)
Ohata, M., Matsuoka, K., Mukai, T.: An adaptive blind separation method using para-Hermitian whitening filter for convolutively mixed signals. Signal Processing 87(1), 33–50 (2007)
Smaragdis, P.: Blind separation of convolved mixtures in the frequency domain[J]. Neurocomputing 22(1-3), 21–34 (1998)
Smaragdis, P.: Convolutive speech bases and their application to supervised speech separation. IEEE Trans. on Audio, Speech and Language Processing 15(1), 1–12 (2007)
Yang, B.: Projection approximation subspace tracking. IEEE Trans. Signal Processing 43(1), 95–107 (1995)
Zhang, X.D.: Matrix analysis and application (Chinese). Tsinghua University Press, China, Beijing (2004)
Zhu, X.L., Zhang, X.D., Su, Y.T.: A fast NPCA algorithm for online blind source separation. Neurocomputing 69(7-9), 964–968 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, L., Li, H. (2007). An Algorithm Based on Nonlinear PCA and Regulation for Blind Source Separation of Convolutive Mixtures. In: Li, K., Fei, M., Irwin, G.W., Ma, S. (eds) Bio-Inspired Computational Intelligence and Applications. LSMS 2007. Lecture Notes in Computer Science, vol 4688. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74769-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-540-74769-7_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74768-0
Online ISBN: 978-3-540-74769-7
eBook Packages: Computer ScienceComputer Science (R0)