Unsupervised Single Channel Source Separation with Nonnegative Matrix Factorization

Abstract

In this paper, a novel single channel source separation using two-dimensional nonnegative matrix factorization (NMF2D) is proposed.In NMF2D, the time-frequency (TF) profile of each source is modeled as two-dimensional convolution of the temporal code and the spectral basis.The proposed model used Beta-divergence as a cost function and updated by maximizing the joint probability of the mixing spectral basis and temporal codes using the multiplicative update rules.Results have concretely shown the effectiveness of the algorithm in blindly separating the audio sources from single channel mixture.