Frequency-domain blind deconvolution based on mutual information rate

In this paper, a new blind single-input single-output (SISO) deconvolution method based on the minimization of the mutual information rate of the deconvolved output is proposed. The method works in the frequency domain and requires estimation of the signal probability density function. Thus, the algorithm uses higher order statistics (except for Gaussian source) and allows non-minimum-phase filter estimation. In practice, the criterion contains a regularization term for limiting noise amplification as in Wiener filtering. The score function estimation, which represents a key point of the algorithm, is detailed, and the most robust estimate is selected. Finally, experiments point to the relevance of the proposed algorithm: 1) any filter, minimum phase or not, can be estimated and 2) on actual data (underwater explosions, seismovolcanic phenomena), this deconvolution algorithm provides good results with a better tradeoff between deconvolution quality and noise amplification than existing methods.

[1]  Jerry M. Mendel,et al.  Maximum likelihood detection and estimation of Bernoulli - Gaussian processes , 1982, IEEE Trans. Inf. Theory.

[2]  L. Vielva,et al.  A fast blind SIMO channel identification algorithm for sparse sources , 2003, IEEE Signal Processing Letters.

[3]  Visa Koivunen,et al.  Source Distribution Adaptive Maximum Likelihood Estimation of ICA Model , 2000 .

[4]  Milton J. Porsani,et al.  Mixed-phase deconvolution , 1998 .

[5]  Michael Zibulevsky,et al.  Underdetermined blind source separation using sparse representations , 2001, Signal Process..

[6]  Francois Combet,et al.  Recovery of a high shock probability process using blind deconvolution , 2002, 2002 11th European Signal Processing Conference.

[7]  Dinh Tuan Pham,et al.  Separation of a mixture of independent sources through a maximum likelihood approach , 1992 .

[8]  Jean-François Bercher,et al.  Estimating the entropy of a signal with applications , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[9]  D. Pham FAST ALGORITHM FOR ESTIMATING MUTUAL INFORMATION, ENTROPIES AND SCORE FUNCTIONS , 2003 .

[10]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[11]  Mouad Boumahdi,et al.  Blind identification using the kurtosis with applications to field data , 1996, Signal Process..

[12]  Olivier Rosec,et al.  Bayesian estimation of non-minimum phase wavelets applied to marine reflection seismic data , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[13]  D. Donoho ON MINIMUM ENTROPY DECONVOLUTION , 1981 .

[14]  Marc Lavielle,et al.  A stochastic algorithm for parametric and non-parametric estimation in the case of incomplete data , 1995, Signal Process..

[15]  Dinh-Tuan Pham,et al.  Fast algorithms for mutual information based independent component analysis , 2004, IEEE Transactions on Signal Processing.

[16]  T. Ens,et al.  Blind signal separation : statistical principles , 1998 .

[17]  Roger P. Hamernik,et al.  Construction of a joint peak-interval histogram using higher-order cumulant-based inverse filtering , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[18]  Jerome Mars,et al.  Applications of autoregressive models and time–frequency analysis to the study of volcanic tremor and long-period events , 2002 .

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

[20]  Visa Koivunen,et al.  Blind Separation Using Characteristic Function Based Criterion , 2001 .

[21]  Marc Lavielle,et al.  Bayesian deconvolution of Bernoulli-Gaussian processes , 1993, Signal Process..

[22]  Philippe Garat,et al.  Blind separation of mixture of independent sources through a quasi-maximum likelihood approach , 1997, IEEE Trans. Signal Process..

[23]  Yves Goussard,et al.  Multichannel seismic deconvolution , 1993, IEEE Trans. Geosci. Remote. Sens..

[24]  Deniz Erdogmus,et al.  Adaptive blind deconvolution of linear channels using Renyi's entropy with Parzen window estimation , 2004, IEEE Transactions on Signal Processing.

[25]  Liqing Zhang,et al.  Multichannel blind deconvolution of nonminimum-phase systems using filter decomposition , 2004, IEEE Transactions on Signal Processing.

[26]  Patrick Duvaut,et al.  Bayesian estimation of state-space models applied to deconvolution of Bernoulli - Gaussian processes , 1997, Signal Process..

[27]  J. Cadzow Blind deconvolution via cumulant extrema , 1996, IEEE Signal Process. Mag..

[28]  Christian Jutten,et al.  Quasi-nonparametric blind inversion of Wiener systems , 2001, IEEE Trans. Signal Process..

[29]  Pierre Comon,et al.  MA identification using fourth order cumulants , 1992, Signal Process..

[30]  D. Pham CONTRAST FUNCTIONS FOR BLIND SEPARATION AND DECONVOLUTION OF SOURCES , 2001 .

[31]  Andrzej Cichocki,et al.  Flexible Independent Component Analysis , 2000, J. VLSI Signal Process..

[32]  Richard M. Everson,et al.  Independent Component Analysis: A Flexible Nonlinearity and Decorrelating Manifold Approach , 1999, Neural Computation.

[33]  B. A. D. H. Brandwood A complex gradient operator and its applica-tion in adaptive array theory , 1983 .

[34]  Jitendra K. Tugnait,et al.  Estimation of linear parametric models using inverse filter criteria and higher order statistics , 1993, IEEE Trans. Signal Process..

[35]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[36]  Liqing Zhang,et al.  Self-adaptive blind source separation based on activation functions adaptation , 2004, IEEE Transactions on Neural Networks.

[37]  A. Bos Complex gradient and Hessian , 1994 .

[38]  Christian Jutten,et al.  MINIMIZATION-PROJECTION (MP) APPROACH FOR BLIND SOURCE SEPARATION IN DIFFERENT MIXING MODELS , 2003 .

[39]  Massoud Babaiezadeh Malmiri On blind source separation in convolutive and nonlinear mixtures , 2002 .

[40]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[41]  Christian Jutten,et al.  Source separation in post-nonlinear mixtures , 1999, IEEE Trans. Signal Process..