Title :
On a new stochastic version of the EM algorithm
Author :
Campbell, Colin ; Godsill, Simon
Author_Institution :
Signal Process. Group, Cambridge Univ., Cambridge, UK
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;
Conference_Titel :
Signal Processing Conference (EUSIPCO 1998), 9th European
Conference_Location :
Rhodes
Print_ISBN :
978-960-7620-06-4
