Blind speech separation for convolutive mixtures using an oriented principal components analysis method

This paper deals with blind speech separation of convolutive mixtures of sources. The separation criterion is based on the Oriented Principal Components Analysis (OPCA) method. OPCA is a (second order) extension of standard Principal Component Analysis (PCA) aiming at maximizing the power ratio of a pair of signals. The convolutive mixing is obtained by modeling the Head Related Transfer Function (HRTF). Experimental results show the efficiency of the proposed approach in terms of subjective and objective evaluation, when compared to the widely used CFICA (Convolutive Fast-ICA) algorithm.