Spatial location priors for Gaussian model based reverberant audio source separation

We consider the Gaussian framework for reverberant audio source separation, where the sources are modeled in the time-frequency domain by their short-term power spectra and their spatial covariance matrices. We propose two alternative probabilistic priors over the spatial covariance matrices which a...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on advances in signal processing 2013-09, Vol.2013 (1), p.1-11, Article 149
Main Authors: Duong, Ngoc Q K, Vincent, Emmanuel, Gribonval, Rémi
Format: Article
Language:English
Subjects:
Algorithms
Computer Science
Covariance
Engineering
Informed Acoustic Source Separation
Mathematical models
Maximum likelihood estimation
Permutations
Power spectra
Probability theory
Quantum Information Technology
Separation
Signal and Image Processing
Signal,Image and Speech Processing
Spintronics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We consider the Gaussian framework for reverberant audio source separation, where the sources are modeled in the time-frequency domain by their short-term power spectra and their spatial covariance matrices. We propose two alternative probabilistic priors over the spatial covariance matrices which are consistent with the theory of statistical room acoustics and we derive expectation-maximization algorithms for maximum a posteriori (MAP) estimation. We argue that these algorithms provide a statistically principled solution to the permutation problem and to the risk of overfitting resulting from conventional maximum likelihood (ML) estimation. We show experimentally that in a semi-informed scenario where the source positions and certain room characteristics are known, the MAP algorithms outperform their ML counterparts. This opens the way to rigorous statistical treatment of this family of models in other scenarios in the future.
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/1687-6180-2013-149