Joint source separation and dereverberation using constrained spectral divergence optimization

A novel method of joint source separation and dereverberation that minimizes the divergence between the observed and true spectral subband envelopes is discussed in this paper. This divergence minimization is carried out within the non-negative matrix factorization (NMF) framework by imposing certain non-negative constraints on the subband envelopes. Additionally, the joint source separation and dereverberation framework described herein utilizes the spectral subband envelope obtained from group delay spectral magnitude (GDSM). In order to obtain the spectral subband envelope from the GDSM, the equivalence of the magnitude and the group delay spectrum via the weighted cepstrum is used. Since the subband envelope of the group delay spectral magnitude is robust and has a high spectral resolution, less error is noted in the NMF decomposition. Late reverberation components present in the separated signals are then removed using a modified spectral subtraction technique. The quality of separated and dereverberated speech signal is evaluated using several objective and subjective criteria. Experiments on distant speech recognition are then conducted at various direct-to-reverberant ratios (DRR) on the GRID corpus. Experimental results indicate significant improvements over existing methods in the literature.