Speech enhancement for non-stationary noise environments

In this paper, we present an optimally-modified log-spectral amplitude (OM-LSA) speech estimator and a minima controlled recursive averaging (MCRA) noise estimation approach for robust speech enhancement. The spectral gain function, which minimizes the mean-square error of the log-spectra, is obtained as a weighted geometric mean of the hypothetical gains associated with the speech presence uncertainty. The noise estimate is given by averaging past spectral power values, using a smoothing parameter that is adjusted by the speech presence probability in subbands. We introduce two distinct speech presence probability functions, one for estimating the speech and one for controlling the adaptation of the noise spectrum. The former is based on the time-frequency distribution of the a priori signal-to-noise ratio. The latter is determined by the ratio between the local energy of the noisy signal and its minimum within a specified time window. Objective and subjective evaluation under various environmental conditions confirm the superiority of the OM-LSA and MCRA estimators. Excellent noise suppression is achieved, while retaining weak speech components and avoiding the musical residual noise phenomena. (C) 2001 Elsevier Science B.V. All rights reserved.