This paper presents an algorithm for nonnegative matrix factorization 2D (NMF-2D) with the flexible β-Divergence. The β-Divergence is a group of cost functions parametrized by a single parameter β. The Least Squares divergence, Kullback-Leibler divergence and the Itakura-Saito divergence are special cases (β=2,1,0). This paper presents a more complete algorithm which uses a flexible range of β, instead of be limited to just special cases. We describe a maximization-minimization (MM) algorithm lead to multiplicative updates. The proposed factorization decomposes an information-bearing matrix into two-dimensional convolution of factor matrices that represent the spectral dictionary and temporal codes with enhanced performance. The method is demonstrated on the separation of audio mixtures recorded from a single channel. Experimental tests and comparisons with other factorization methods have been conducted to verify the efficacy of the proposed method.
|Title of host publication
|Electronic Proceedings of the 2015 IEEE International Workshop on Signal Processing Systems, SiPS 2015
|Published - 3 Dec 2015
|IEEE International Workshop on Signal Processing Systems, SiPS 2015 - Hangzhou, China
Duration: 14 Oct 2015 → 16 Oct 2015
|IEEE International Workshop on Signal Processing Systems, SiPS 2015
|14/10/15 → 16/10/15