Speech enhancement employing Laplacian-Gaussian mixture

73 p.This dissertation reports my work on speech enhancement incorporating statistical modelling of speech signals. In this low complexity speech enhancement algorithm (SEA), a noisy speech signal is first decorrelated and then the clean speech components are estimated from the decorrelated noisy speech samples. The probability density distributions of clean speech and noise signals are assumed to be Laplacian and Gaussian, respectively. The clean speech components are estimated either by Maximum Likelihood (ML) or Minimum-Mean-Square-Error (MMSE) estimators. These estimators require some statistical parameters that can be estimated from the noisy speech. These parameters are adaptively extracted by the ML approach during the active speech or silence intervals, respectively.Master of Science (Signal Processing