DocumentCode
703173
Title
On a new stochastic version of the EM algorithm
Author
Campbell, Colin ; Godsill, Simon
Author_Institution
Signal Process. Group, Cambridge Univ., Cambridge, UK
fYear
1998
fDate
8-11 Sept. 1998
Firstpage
1
Lastpage
4
Abstract
We present an algorithm in which the Maximisation step of the EM algorithm is replaced by a Sampling step. We describe an application of the algorithm to noise reduction for an audio signal. The results of various simulations on synthetic data are presented and compared to the results obtained using the EM algorithm and the Gibbs Sampler. A major limitation of the EM algorithm is that it can converge on local stationary points. The results we present show how our algorithm successfully overcomes this limitation.
Keywords
Markov processes; Monte Carlo methods; audio signal processing; expectation-maximisation algorithm; signal sampling; EM algorithm; Gibbs sampler; audio signal; local stationary points; noise reduction; stochastic version; synthetic data; Approximation algorithms; Autoregressive processes; Convergence; Mathematical model; Multiple signal classification; Signal processing algorithms; Stochastic processes;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Conference (EUSIPCO 1998), 9th European
Conference_Location
Rhodes
Print_ISBN
978-960-7620-06-4
Type
conf
Filename
7089643
Link To Document