Generalized mutual information approach to multichannel blind deconvolution

Authors:
Dinh-Tuan Pham
Affiliations:
Laboratoire de Modélisation et Calcul, BP 53, 38041 Grenoble, Cedex, France
Venue:
Signal Processing
Year:
2007

Citing 11
Cited 1

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Multiple-input-multiple-output blind system identification based on cross-polyspectra

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 01
Fast algorithms for mutual information based independent component analysis

IEEE Transactions on Signal Processing - Part I
Super-exponential algorithms for multichannel blind deconvolution

IEEE Transactions on Signal Processing
A family of frequency- and time-domain contrasts for blind separation of convolutive mixtures of temporally dependent signals

IEEE Transactions on Signal Processing
Cumulant-based blind identification of linearmulti-input-multi-output systems driven by colored inputs

IEEE Transactions on Signal Processing
Criteria for multichannel signal separation

IEEE Transactions on Signal Processing
Identification and deconvolution of multichannel linearnon-Gaussian processes using higher order statistics and inverse filtercriteria

IEEE Transactions on Signal Processing
Blind separation of instantaneous mixture of sources via anindependent component analysis

IEEE Transactions on Signal Processing
Quasi-nonparametric blind inversion of Wiener systems

IEEE Transactions on Signal Processing
Frequency domain blind MIMO system identification based on second and higher order statistics

IEEE Transactions on Signal Processing

Geodesic-based and projection-based neural blind deconvolution algorithms

Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

In this paper, we propose an approach to the multichannel blind deconvolution problem, based on the mutual information criterion and more generally on an appropriate system of estimating equations. Formulas for the quasi-Newton algorithm and the asymptotic covariance matrix of the estimator are provided. More interesting results have been obtained in the pure deconvolution case. By a clever parameterization of the deconvolution filter, the estimated parameters are asymptotically independent and explicit and simple formula for their variance are obtained. The quasi-Newton algorithm also becomes particularly simple. Simulation results showing the good performance of the methods are provided.