The Application of Laplacian Mixture Model in Speech Enhancement

In this paper an estimator for speech enhancement based on Laplacian Mixture Model has been proposed. The proposed method, estimates the complex DFT coefficients of clean speech from noisy speech using the MMSE estimator, when the clean speech DFT coefficients are supposed mixture of Laplacians and the DFT coefficients of noise are assumed zero-mean Gaussian distribution. For estimating the Laplacian Mixture model parameters, Expectation-Maximization algorithm is used.The segmental Signal to Noise Ratio, Log-Likelihood Ratio and Perceptual Evaluation of Speech Quality measures are used for objective evaluation of the proposed method. It is shown that the proposed estimator, in term of these objective measures, has better performance than two estimators based on single Gaussian and another estimator based on single Laplacian model.