Continuous wavelet transform based source separation

Abstract

Separation of convolutive mixtures of speech sources is considered in this paper. Several approaches have been reported in the literature using statistical methods as well as transforms such as the short time Fourier transform (STFT) and the Paquet wavelet transform (PWT). In this paper we propose a new source separation method based on the independent component analysis (ICA) and utilizing the continuous wavelet transform (CWT). The experimental results obtained by our method have been investigated and compared with those generated by other approaches.