DocumentCode
353206
Title
On-line non-stationary ICA using mixture models
Author
Ahmed, A. ; Andrieu, C. ; Doucet, A. ; Rayner, P.J.W.
Author_Institution
Dept. of Eng., Cambridge Univ., UK
Volume
5
fYear
2000
fDate
2000
Firstpage
3148
Abstract
In this paper we address the problem of on-line source separation with sources modelled as mixtures of Gaussians which are linearly combined via a series of non-stationary mixing matrices. The online recovery of the sources from the observations is a non-linear statistical filtering problem that we address using state of the art particle filter methods. Simulations are presented and satisfactory results are obtained
Keywords
Gaussian processes; array signal processing; digital filters; iterative methods; matrix algebra; Gaussians; independent component analysis; nonlinear statistical filtering problem; nonstationary mixing matrices; online nonstationary ICA using mixture models; online recovery; online source separation; particle filter methods; Approximation algorithms; Blind source separation; Crosstalk; Delay; Filtering; Independent component analysis; Particle filters; Signal processing; Source separation; State-space methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location
Istanbul
ISSN
1520-6149
Print_ISBN
0-7803-6293-4
Type
conf
DOI
10.1109/ICASSP.2000.861205
Filename
861205
Link To Document