Publication detail
Plug-and-play audio restoration with diffusion denoiser
ŠVENTO, M. RAJMIC, P. MOKRÝ, O.
Original Title
Plug-and-play audio restoration with diffusion denoiser
Type
conference paper
Language
English
Original Abstract
There have been a plethora of methods developed to tackle diverse audio reconstruction problems. Recently, deep generative models have affected this field strongly, some of them allowing to solve multiple problems with only a minimal need for adaptation. However, long inference times still represent a barrier to their real-world deployment. We propose a plug-and-play approach to audio reconstruction enabling a shorter duration of signal generation. We present our approach on a number of inverse problems, all evaluated on a piano sound dataset. Subjectively, the proposed strategy performs competitively with recent methods, however, this is rarely reflected by objective metrics.
Keywords
diffusion model, plug-and-play, audio restoration, reconstruction, declipping, denoising, inpainting
Authors
ŠVENTO, M.; RAJMIC, P.; MOKRÝ, O.
Released
4. 10. 2024
Publisher
IEEE
Location
Aalborg, Denmark
ISBN
979-8-3503-6185-8
Book
2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)
Pages from
115
Pages to
119
Pages count
5
URL
BibTex
@inproceedings{BUT189097,
author="Michal {Švento} and Pavel {Rajmic} and Ondřej {Mokrý}",
title="Plug-and-play audio restoration with diffusion denoiser",
booktitle="2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)",
year="2024",
pages="115--119",
publisher="IEEE",
address="Aalborg, Denmark",
doi="10.1109/IWAENC61483.2024.10694642",
isbn="979-8-3503-6185-8",
url="https://ieeexplore.ieee.org/document/10694642"
}