Audio Barlow twins: self-supervised audio representation learning
File(s)
Accepted version
Author(s)
Anton, Jonah
Coppock, Harry
Shukla, Pancham
Schuller, Björn W
Type
Conference Paper
Abstract
The Barlow Twins self-supervised learning objective requires neither negative samples or asymmetric learning updates, achieving results on a par with the current state-of-the-art within Computer Vision. As such, we present Audio Barlow Twins, a novel self-supervised audio representation learning approach, adapting Barlow Twins to the audio domain. We pre-train on the large-scale audio dataset AudioSet, and evaluate the quality of the learnt representations on 18 tasks from the HEAR 2021 Challenge, achieving results which outperform, or otherwise are on a par with, the current state-of-the-art for instance discrimination self-supervised learning approaches to audio representation learning. Code at https://github.com/jonahanton/SSL_audio.
Date Issued
2023-06-05
Date Acceptance
2023-02-15
Citation
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Publisher
IEEE
Journal / Book Title
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Copyright Statement
Copyright © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
http://dx.doi.org/10.1109/icassp49357.2023.10095041
Source
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publication Status
Published
Start Date
2023-06-04
Finish Date
2023-06-10
Coverage Spatial
Rhodes Island, Greece