A New Method Based on Spectral Subtraction for Speech Dereverberation

A new monaural method for the suppression of late room reverberation from speech signals, based on spectral subtraction, is presented. The problem of reverberation suppression differs from classical speech de-noising in that the "reverberation noise" is non stationary. In this paper, the use of a novel estimator of the non-stationary reverberation-noise power spectrum, based on a statistical model of late reverberation, is presented. The algorithm is tested on real reverberated signals. The performances for different RIRs with T_r ranging from 0.34 s to 1.7 s consistently show significant noise reduction with little signal distortion. Moreover, when used as a front end to an automatic speech recognition system, the algorithm brings about dramatic improvements in terms of automatic speech recognition scores in various reverberant environments.