A Partially Collapsed Gibbs Sampler for Unsupervised Nonnegative Sparse Signal Restoration

A Partially Collapsed Gibbs Sampler for Unsupervised Nonnegative Sparse Signal Restoration

In this paper the problem of restoration of unsupervised nonnegative sparse signals is addressed in the Bayesian framework. We introduce a new probabilistic hierarchical prior, based on the Generalized Hyperbolic (GH) distribution, which explicitly accounts for sparsity. On the one hand, this new pr...

Full description

Saved in:
Bibliographic Details
Published in:ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5519 - 5523
Main Authors: Amrouche, M. C., Carfantan, H., Idier, J.
Format: Conference Proceeding
Language:English
Published: IEEE 06-06-2021
Subjects:
Acceleration
Acoustics
Bayes methods
Conferences
Probabilistic logic
Signal restoration
Speech processing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper the problem of restoration of unsupervised nonnegative sparse signals is addressed in the Bayesian framework. We introduce a new probabilistic hierarchical prior, based on the Generalized Hyperbolic (GH) distribution, which explicitly accounts for sparsity. On the one hand, this new prior allows us to take into account the non-negativity. On the other hand, thanks to the decomposition of GH distributions as continuous Gaussian mean-variance mixture, a partially collapsed Gibbs sampler (PCGS) implementation is made possible, which is shown to be more efficient in terms of convergence time than the classical Gibbs sampler.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414293