Audio Declipping with Unfolded Douglas-Rachford Algorithm

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0197732" target="_blank" >RIV/00216305:26220/26:0197732 - isvavai.cz</a>
Result on the web
<a href="https://dspace.vut.cz/items/3ddfdf2f-e304-436a-9e23-1bbe58d83fae" target="_blank" >https://dspace.vut.cz/items/3ddfdf2f-e304-436a-9e23-1bbe58d83fae</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.13164/eeict.2025.145" target="_blank" >10.13164/eeict.2025.145</a>

Result language
angličtina
Original language name
Audio Declipping with Unfolded Douglas-Rachford Algorithm
Original language description
This paper addresses the problem of audio declipping, which occurs when audio signals exceed a certain level, causing distortion and loss of information. To enhance existing methods, we propose a novel solution combining deep unfolding with the Douglas–Rachford algorithm (DRA) within an optimization framework, offering a blend of deep learning and optimization. The declipping problem is formulated as an optimization task that aims to recover the original signal by minimizing sparsity in the time-frequency domain. Our approach transforms each iteration of DRA into a layer of a neural network, optimizing parameters based on training data. Experimental results demonstrate that the unrolled DRA (uDRA) achieves short inference time compared to classical declipping methods, although it does not yet match them in terms of restoration quality. This work highlights the potential of deep unfolding for efficient audio declipping, with future improvements needed to capture the complexities of audio distortion more effectively.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA23-07294S" target="_blank" >GA23-07294S: From perceptron to perception: psychoacoustically motivated audio reconstruction using learned components</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings II of the 31st Student EEICT 2025 (Selected Papers)
ISBN
978-80-214-6320-2
ISSN
—
e-ISSN
2788-1334
Number of pages
4
Pages from-to
145-148
Publisher name
—
Place of publication
—
Event location
Brno
Event date
Apr 29, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)