New adaptive speech enhancement system using a novel wavelet thresholding technique

A new adaptive speech enhancement system, which utilizes a second-generation wavelet transform (SGWT) decomposition and a novel adaptive subband thresholding technique, is presented. The adaptive thresholding technique is based on accurate estimation of subband segmental signal-to-noise ratio (SegSNR) and voiced/unvoiced classification of the speech. First, the speech signal is segmented and each segment is decomposed into a number of wavelet bands using the SGWT. Each segment is then classified as voiced/unvoiced, and the subband noise level is estimated using a minimum variance approach. Finally a softthresholding gain function is applied on each band. The gain function is adapted based on the estimated (SegSNR) and on whether the processed segment is voiced or unvoiced. The proposed system has been tested with various types of noise. Reported results show that the system provides high-level of noise suppression while preserving the intelligibility and naturalness of the speech.