Audio Barlow Twins: Self-Supervised Audio Representation Learning

Autor:	Anton, Jonah, Coppock, Harry, Shukla, Pancham, Schuller, Bjorn W.
Rok vydání:	2022
Předmět:	Computer Science - Sound Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: 15 pages (4 main text, rest references + appendices)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.14345 Zobrazit plný text záznamu View this record from Arxiv