Mixtures of Gamma Priors for Non-negative Matrix Factorization Based Speech Separation

Authors:
Tuomas Virtanen;Ali Taylan Cemgil
Affiliations:
Tampere Univ. of Technology, Tampere, Finland FI-33720;Dept. of Computer Eng., Boğaziçi University, Istanbul, Turkey TR-34342
Venue:
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Year:
2009

Citing 1
Cited 3

Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria

IEEE Transactions on Audio, Speech, and Language Processing

The Markov selection model for concurrent speech recognition

Neurocomputing
Audio source separation using hierarchical phase-invariant models

NOLISP'09 Proceedings of the 2009 international conference on Advances in Nonlinear Speech Processing
Regularized nonnegative matrix factorization using Gaussian mixture priors for supervised single channel source separation

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with audio source separation using supervised non-negative matrix factorization (NMF). We propose a prior model based on mixtures of Gamma distributions for each sound class, which hyperparameters are trained given a training corpus. This formulation allows adapting the spectral basis vectors of the sound sources during actual operation, when the exact characteristics of the sources are not known in advance. Simulations were conducted using a random mixture of two speakers. Even without adaptation the mixture model outperformed the basic NMF, and adaptation furher improved slightly the separation quality. Audio demonstrations are available at www.cs.tut.fi/~tuomasv .