ALGORITHMS FOR MARKOVIAN SOURCE SEPARATION BY ENTROPY RATE MINIMIZATION

被引：0

作者：

Fu, Geng-Shen ^{[1
]}

Phlypo, Ronald ^{[1
]}

Anderson, Matthew ^{[1
]}

Li, Xi-Lin ^{[2
]}

Adali, Tuelay ^{[1
]}

机构：

[1] Univ Maryland Baltimore Cty, Dept CSEE, Baltimore, MD 21250 USA

[2] Fortemedia, Sunnyvale, CA 94086 USA

来源：

2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2013年

关键词：

Blind source separation; Independent component analysis; Mutual information rate; Markov model; BLIND SEPARATION;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Since in many blind source separation applications, latent sources are both non-Gaussian and have sample dependence, it is desirable to exploit both non-Gaussianity and sample dependency. In this paper, we use the Markov model to construct a general framework for the analysis and derivation of algorithms that take both properties into account. We also present two algorithms using two effective source priors. The first one is a multivariate generalized Gaussian distribution and the second is an autoregressive model driven by a generalized Gaussian distributed process. We derive the Cramer-Rao lower bound and demonstrate that the performance of the algorithms approach the lower bound especially when the underlying model matches the parametric model. We also demonstrate that a flexible semi-parametric approach exhibits very desirable performance.

引用

页码：3248 / 3252

页数：5