Mixture-model-based signal denoising

This paper proposes a new signal denoising methodology for dealing with asymmetrical noises. The adopted strategy is based on a regression model where the noise is supposed to be additive and distributed following a mixture of Gaussian densities. The parameters estimation is performed using a Generalized EM (GEM) algorithm. Experimental studies on simulated and real signals in the context of a diagnosis application in the railway domain reveal that the proposed approach performs better than the least-squares and wavelets methods.