Speech Enhancement for Non-Stationary Noise Environments

This paper proposes an algorithm improved over MMSE-LSA Algorithm. It suits non-stationary noise environments better than the traditional algorithm. The main part of this method is the estimation of noise, which is updated using time-frequency smoothing factors calculated based on speech-present probability in each frequency bin of the noisy speech spectrum. It could keep up with the noise change closely. Objective tests show that the proposed algorithm is superior to the traditional MMSE-LSA method in noise-tracking and mean opinion score.