Audio Barlow Twins: Self-Supervised Audio Representation Learning
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.
Cite
@article{arxiv.2209.14345,
title = {Audio Barlow Twins: Self-Supervised Audio Representation Learning},
author = {Jonah Anton and Harry Coppock and Pancham Shukla and Bjorn W. Schuller},
journal= {arXiv preprint arXiv:2209.14345},
year = {2022}
}
Comments
15 pages (4 main text, rest references + appendices)