English

Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation

Sound 2023-03-08 v1 Audio and Speech Processing

Abstract

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its success, this idea can suffer from a collapsing issue where the network produces a constant representation. To this end, we introduce SELFIE, a novel Self-supervised Learning approach for audio representation via Feature Diversity and Decorrelation. SELFIE avoids the collapsing issue by ensuring that the representation (i) maintains a high diversity among embeddings and (ii) decorrelates the dependencies between dimensions. SELFIE is pre-trained on the large-scale AudioSet dataset and its embeddings are validated on nine audio downstream tasks, including speech, music, and sound event recognition. Experimental results show that SELFIE outperforms existing SSL methods in several tasks.

Keywords

Cite

@article{arxiv.2303.03717,
  title  = {Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation},
  author = {Bac Nguyen and Stefan Uhlich and Fabien Cardinaux},
  journal= {arXiv preprint arXiv:2303.03717},
  year   = {2023}
}

Comments

ICASSP 2023

R2 v1 2026-06-28T09:05:02.315Z