A modeling and algorithmic framework for (non)social (co)sparse audio restoration. Gaultier, C., Bertin, N., Kitić, S., & Gribonval, R. arXiv:1711.11259 [cs, eess], November, 2017. arXiv: 1711.11259
A modeling and algorithmic framework for (non)social (co)sparse audio restoration [link]Paper  abstract   bibtex   
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.
@article{gaultier_modeling_2017,
	title = {A modeling and algorithmic framework for (non)social (co)sparse audio restoration},
	url = {http://arxiv.org/abs/1711.11259},
	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.},
	urldate = {2022-03-02},
	journal = {arXiv:1711.11259 [cs, eess]},
	author = {Gaultier, Clément and Bertin, Nancy and Kitić, Srđan and Gribonval, Rémi},
	month = nov,
	year = {2017},
	note = {arXiv: 1711.11259},
	keywords = {Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},
}

Downloads: 0