A METHOD OF BLIND SEPARATION ON TEMPORAL STRUCTURE OF SIGNALS

In this article, we propose an Blind Source Separation algorithm for convolutive mixture of signals. We propose a method of separating signals in the time-frequency domain. We apply the decorrelation method proposed by Molgedey and Schuster on spectrogram and reconstruct separated signals focusing on the temporal structure of the signals. We show some results of experiments with both artificially controlled data and speech data recorded in the real environment.

[1]  Antoine Souloumiac,et al.  Jacobi Angles for Simultaneous Diagonalization , 1996, SIAM J. Matrix Anal. Appl..

[2]  Andreas Ziehe,et al.  Combining time-delayed decorrelation and ICA: towards solving the cocktail party problem , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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

[4]  Andrzej Cichocki,et al.  Neural networks for blind decorrelation of signals , 1997, IEEE Trans. Signal Process..

[5]  Paris Smaragdis,et al.  Blind separation of convolved mixtures in the frequency domain , 1998, Neurocomputing.

[6]  H. G. Schuster,et al.  Blind separation of convolutive mixtures , 1997, Proceedings of 40th Midwest Symposium on Circuits and Systems. Dedicated to the Memory of Professor Mac Van Valkenburg.

[7]  Schuster,et al.  Separation of a mixture of independent signals using time delayed correlations. , 1994, Physical review letters.