LAUSR

In this paper, we address the problem of speech enhancement by adaptive filtering algorithms. A particular attention has been paid to the backward blind source separation (BBSS) algorithm and its use in crosstalk resistant speech enhancement applications. In this paper, we propose to implement the BBSS algorithm in the wavelet-domain. The proposed backward wavelet BBSS (WBBSS) algorithm is then used in speech enhancement application when important crosstalk interferences are presents. The new WBBSS algorithm shows better performances in terms of convergence speed and steady state in comparison with the classical BBSS one. The performances properties of the proposed algorithm are evaluated in term of segmental SNR (SegSNR), segmental mean square error (SegMSE), and cepstral distance (CD) criteria. The obtained results have confirmed the best performance of the proposed WBBSS algorithm in a lot of situations when blind noisy observations are available.