论文信息 - Stability study for source separation in convolutive mixtures of two sources

Stability study for source separation in convolutive mixtures of two sources

Abstract Blind separation of sources in convolutive mixtures involves the stability of an IIR filter for both direct and recursive structures. In this communication, in the case of two convolutive mixtures of two sources, we are interested in sufficient conditions on mixture filters which imply the stability of this IIR filter. Various stability criteria of IIR filters are studied in order to obtain a simple condition for stability.

[1] Lennart Ljung,et al. On positive real transfer functions and the convergence of some recursive schemes , 1977 .

[2] W. Rogosinski,et al. The Geometry of the Zeros of a Polynomial in a Complex Variable , 1950, The Mathematical Gazette.

[3] 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.

[4] Ehud Weinstein,et al. Criteria for multichannel signal separation , 1994, IEEE Trans. Signal Process..

[5] Dirk Van Compernolle,et al. Signal separation by symmetric adaptive decorrelation: stability, convergence, and uniqueness , 1995, IEEE Trans. Signal Process..

[6] Christian Jutten,et al. Blind source separation for convolutive mixtures , 1995, Signal Process..

[7] Dirk Van Compernolle,et al. Feedforward and feedback in a symmetric adaptive noise canceler : “stability analysis in a simplified case” , 1992 .

[8] Miguel Angel Lagunas,et al. Blind wideband source separation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[9] E. I. Jury,et al. Theory and application of the z-transform method , 1965 .

[10] Jont B. Allen,et al. Image method for efficiently simulating small‐room acoustics , 1976 .