A Time-Recursive Adaptive Algorithm for Colored Noise Reduction in Speech Enhancement

摘要

We propose an improved spectral subtraction method for the reduction of colored acoustic noise added to the speech. Our implementation uses a time-recursive algorithm for estimation of the noise power spectral density and a multi-band spectral over subtraction method to reduce the colored noise. Simulations show a better quality in terms of Itakura Saito distance and perceptual evaluation of quality for the enhanced speech. Using the proposed speech enhancement method, a very good speech quality with less musical noise and with minimal speech distortion is obtained.