Audio Barlow Twins: Self-Supervised Audio Representation Learning

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 this https URL.

Download paper here

@INPROCEEDINGS{10095041,
  author={Anton, Jonah and Coppock, Harry and Shukla, Pancham and Schuller, Björn W.},
  booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Audio Barlow Twins: Self-Supervised Audio Representation Learning}, 
  year={2023},
  volume={},
  number={},
  pages={1-5},
  keywords={Representation learning;Training;Computer vision;Adaptation models;Codes;Self-supervised learning;Acoustics},
  doi={10.1109/ICASSP49357.2023.10095041}}