Benoit Champagne1, Eric Plourde2, Hanwook Chung1
13:30 - 13:50 | Tue 22 Mar | Room 3C+3D | MLSP-L1.1
In this paper, we propose a basis compensation algorithm for nonnegative matrix factorization (NMF) models as applied to supervised single-channel speech enhancement. In the proposed framework, we use extra free basis vectors for both the clean speech and noise during the enhancement stage in order to capture the features which are not included in the training data. Specifically, the free basis vectors of the clean speech are obtained by exploiting a priori knowledge based on a Gamma distribution. The free bases of the noise are estimated using a regularization approach, which enforces them to be orthogonal to the clean speech and noise basis vectors estimated during the training stage. Experimental results show that the proposed NMF algorithm with basis compensation provides better performance in speech enhancement than the benchmark algorithms.