Compensation of Channel and Noise Distortions Combining Maximum Likelihood based Spectral Subtraction and Normalization

Channel distortion may dramatically degrade speech recognition performance in a distant environment. Authors in their recent work proposed a novel spectral subtraction method which they named it maximum likelihood based spectral subtraction (MLBSS). They indicated that recognition performance could be improved dramatically by adjusting filter parameters based on recognition results. Previous results show effectiveness of this method in dealing with additive distortion. In this paper we propose an approach for increasing robustness of this method against channel distortion in distant talking environment. We add Cepstral Mean Normalization (CMN) in designing MLBSS filter and show that by incorporating this method into design strategy; we can use benefits of both methods. Speech recognition experiments performed in a real distant-talking environment confirm the efficiency of the proposed approach.