Adaptive unsupervised separation of discrete sources

Abstract This paper treats source separation with the help of contrast functions and proposes corresponding adaptive implementations. Its major contributions are two-fold: (i) it proposes a new contrast which can be evaluated without pre-whitening the signals, provided all have unitary power. Its adaptive maximization involves an output AGC for each source recovery and performs as well as separation with pre-whitened signals; (ii) in case of sources with discrete alphabet, an intermediate contrast is proposed which takes additional advantage of the alphabet knowledge. The improvement to source separation is significant for correlated signals, but for adaptively pre-whitened separation, the quality of whitening conditions the improvement.

[1]  Jean-Louis Lacoume,et al.  Separation of independent sources from correlated inputs , 1992, IEEE Trans. Signal Process..

[2]  Nathalie Delfosse,et al.  Adaptive separation of independent sources: a deflation approach , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Y. Sato,et al.  A Method of Self-Recovering Equalization for Multilevel Amplitude-Modulation Systems , 1975, IEEE Trans. Commun..

[4]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[5]  Christian Jutten,et al.  Fourth-order criteria for blind sources separation , 1995, IEEE Trans. Signal Process..

[6]  Eric Moreau,et al.  High order contrasts for self-adaptive source separation criteria for complex source separation , 1996 .

[7]  D. Godard,et al.  Self-Recovering Equalization and Carrier Tracking in Two-Dimensional Data Communication Systems , 1980, IEEE Trans. Commun..

[8]  B. Friedlander,et al.  Blind multi-channel system identification and deconvolution: performance bounds , 1996, Proceedings of 8th Workshop on Statistical Signal and Array Processing.

[9]  Meir Feder,et al.  Multi-channel signal separation by decorrelation , 1993, IEEE Trans. Speech Audio Process..

[10]  A. Benveniste,et al.  Robust identification of a nonminimum phase system: Blind adjustment of a linear equalizer in data communications , 1980 .

[11]  Eweda Eweda,et al.  Convergence analysis of self-adaptive equalizers , 1984, IEEE Trans. Inf. Theory.

[12]  Eric Moreau,et al.  Self-adaptive source separation .I. Convergence analysis of a direct linear network controlled by the Herault-Jutten algorithm , 1997, IEEE Trans. Signal Process..

[13]  J. Cardoso.  On the Performance of Orthogonal Source Separation Algorithms , 1994 .

[14]  J. E. Mazo,et al.  Analysis of decision-directed equalizer convergence , 1980, The Bell System Technical Journal.

[15]  E. Moreau.  Apprentissage et adaptativite. Separation auto-adaptative de sources independantes , 1995 .

[16]  Nathalie Delfosse,et al.  Adaptive blind separation of independent sources: A deflation approach , 1995, Signal Process..

[17]  Yeheskel Bar-Ness,et al.  An IF Cross-Pol Canceller for Microwave Radio Systems , 1987, IEEE J. Sel. Areas Commun..

[18]  Odile Macchi,et al.  Adaptive Processing: The Least Mean Squares Approach with Applications in Transmission , 1995 .

[19]  O. Macchi,et al.  Égalisation adaptative autodidacte par rétroprédiction et prédiction , 1993 .

[20]  E. Moreau,et al.  Multichannel blind signal deconvolution using high order statistics , 1996, Proceedings of 8th Workshop on Statistical Signal and Array Processing.

[21]  Giancarlo Prati,et al.  Blind Equalization and Carrier Recovery Using a "Stop-and-Go" Decision-Directed Algorithm , 1987, IEEE Trans. Commun..

[22]  Pierre Priouret,et al.  Adaptive Algorithms and Stochastic Approximations , 1990, Applications of Mathematics.

[23]  Jean-François Cardoso,et al.  Equivariant adaptive source separation , 1996, IEEE Trans. Signal Process..

[24]  H. Sahlin,et al.  The asymptotic Cramer-Rao lower bound for blind signal separation , 1996, Proceedings of 8th Workshop on Statistical Signal and Array Processing.

[25]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..