English

Unsupervised Discriminative Learning of Sounds for Audio Event Classification

Sound 2021-05-21 v2 Computer Vision and Pattern Recognition Audio and Speech Processing

Abstract

Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet. While this process allows knowledge transfer across different domains, training a model on large-scale visual datasets is time consuming. On several audio event classification benchmarks, we show a fast and effective alternative that pre-trains the model unsupervised, only on audio data and yet delivers on-par performance with ImageNet pre-training. Furthermore, we show that our discriminative audio learning can be used to transfer knowledge across audio datasets and optionally include ImageNet pre-training.

Keywords

Cite

@article{arxiv.2105.09279,
  title  = {Unsupervised Discriminative Learning of Sounds for Audio Event Classification},
  author = {Sascha Hornauer and Ke Li and Stella X. Yu and Shabnam Ghaffarzadegan and Liu Ren},
  journal= {arXiv preprint arXiv:2105.09279},
  year   = {2021}
}

Comments

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 978-1-7281-7605-5/20/$31.00 (c) 2021 IEEE | DOI: 10.1109/ICASSP39728.2021.9413482

R2 v1 2026-06-24T02:16:19.466Z