Publication detail

Joint audio denoising and inpainting with plug-and-play proximal algorithm

ŠVENTO, M. MOKRÝ, O.

Original Title

Joint audio denoising and inpainting with plug-and-play proximal algorithm

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

We propose plug-and-play variant of the Douglas–Rachford proximal algorithm for audio inpainting, which replaces a proximal step with a denoiser. In our situation, the observed samples are further degraded by noise. We demonstrate that the plug-and-play aproach has potential to succeed in this joint task of inpainting and denoising. Objective metrics show that the new method outperforms a conventional counterpart and that it is less sensitive to model hyperparameters.

Keywords

speech enhancement; deep learning; denoising; Douglas–Rachford algorithm; inpainting

Authors

ŠVENTO, M.; MOKRÝ, O.

Released

25. 4. 2023

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-6153-6

Book

Proceedings I of the 29th Student EEICT 2023 (General Papers)

Edition

1

Pages from

214

Pages to

217

Pages count

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf

BibTex

@inproceedings{BUT184260,
  author="Michal {Švento} and Ondřej {Mokrý}",
  title="Joint audio denoising and inpainting with plug-and-play proximal algorithm",
  booktitle="Proceedings I of the 29th Student EEICT 2023 (General Papers)",
  year="2023",
  series="1",
  pages="214--217",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6153-6",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf"
}