Noise cancellation in speech using optimized subband adaptive filtering

Abstract

In this paper, an optimized subband noise canceller for speech signals is developed. The canceller uses a two fold oversampled filter bank. The prototype filter of the filter bank is optimized for minimum system distortion. A variable step size least mean square LMS adaptive filter is used in each subband. Performance under white and colored environments is evaluated in terms of mean square error MSE performance. Comparison is made with a similar model that is based on a standard critically sampled filter banks. Fullband version is used as reference for the canceller outperformed both critically sampled and fullband models.