A modeling and algorithmic framework for (non)social (co)sparse audio restoration

Abstract : We propose a unified modeling and algorithmic framework for audio restoration problem. It encompasses analysis sparse priors as well as more classical synthesis sparse priors, and regular sparsity as well as various forms of structured sparsity embodied by shrinkage operators (such as social shrinkage). The versatility of the framework is illustrated on two restoration scenarios: denoising, and declipping. Extensive experimental results on these scenarios highlight both the speedups of 20% or even more offered by the analysis sparse prior, and the substantial declipping quality that is achievable with both the social and the plain flavor. While both flavors overall exhibit similar performance, their detailed comparison displays distinct trends depending whether declipping or denoising is considered.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-01649261
Contributor : Clément Gaultier <>
Submitted on : Wednesday, November 29, 2017 - 5:16:28 PM
Last modification on : Friday, September 13, 2019 - 9:50:02 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01649261, version 1
  • ARXIV : 1711.11259

Citation

Clément Gaultier, Nancy Bertin, Srđan Kitić, Rémi Gribonval. A modeling and algorithmic framework for (non)social (co)sparse audio restoration. 2017. ⟨hal-01649261⟩

Share

Metrics

Record views

1841

Files downloads

132