Noise reduction using reliable a posteriori Signal-to-Noise Ratio features

This paper addresses the problem of single microphone speech enhancement in noisy environments. State of the art short-time noise reduction techniques are most often expressed as a spectral gain depending on Signal-to-Noise Ratio (SNR). The well-known decision-directed approach drastically limits the level of musical noise but the estimated a priori SNR is biased since it depends on the speech spectrum estimated in the previous frame. The consequence of this bias is an annoying reverberation effect. We propose a method, called Reliable Features Selection Noise Reduction (RFSNR) technique, capable of classifying the a posteriori SNR estimates into two categories: the reliable features leading to speech components and the unreliable ones corresponding to musical noise only. Then it is possible to directly enhance speech using these reliable components thus obtaining an unbiased estimator.