An MA model based blind source separation algorithm

Author

Liu, Ju ; Li, Ke ; He, Zhenya ; Mei, Liangmo

Author_Institution

Dept. of Radio Eng., Southeast Univ., Nanjing, China

Volume

2

fYear

1999

fDate

36495

Firstpage

1363

Abstract

We give a maximum entropy or maximum likelihood approach for blind source separation (BSS). This approach model the sources as filtered versions of white zero-mean signals by a class of moving average (MA) filters. We consider not only the effect of instantaneous measurements, but also the effect of delayed measurements. Compared to the dynamic component analysis (DCA) algorithm, we do not need to estimate the large number of the parameters of the probability density function (PDF) model of white signals. The proposed algorithm can separate the mixture of Gaussian sources

Keywords

Gaussian noise; delays; filtering theory; maximum entropy methods; maximum likelihood estimation; moving average processes; probability; signal processing; white noise; DCA algorithm; Gaussian noise; Gaussian sources mixture; MA model; MLE; PDF model; blind source separation algorithm; delayed measurements; dynamic component analysis; filtered white zero-mean signals; instantaneous measurements; maximum entropy; maximum likelihood approach; moving average filters; probability density function; speech signal; Array signal processing; Blind source separation; Delay effects; Entropy; Filters; Independent component analysis; Maximum likelihood estimation; Neural networks; Signal processing algorithms; Source separation;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 99. Proceedings of the IEEE Region 10 Conference

Conference_Location

Cheju Island

Print_ISBN

0-7803-5739-6

Type

conf

DOI

10.1109/TENCON.1999.818683

Filename

818683