A Statistical Model-Based Speech Enhancement Using Acoustic Noise Classification for Robust Speech Communication

In this paper, we present a speech enhancement technique based on the ambient noise classification that incorporates the Gaussian mixture model (GMM). The principal parameters of the statistical modelbased speech enhancement algorithm such as the weighting parameter in the decision-directed (DD) method and the long-term smoothing parameter of the noise estimation, are set according to the classified context to ensure best performance under each noise. For real-time context awareness, the noise classification is performed on a frame-by-frame basis using the GMM with the soft decision framework. The speech absence probability (SAP) is used in detecting the speech absence periods and updating the likelihood of the GMM. key words: statistical model-based speech enhancement, Gaussian mixture model, noise classification