yangdongchao / uclser20

Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations"

uclser20

This repository will contain the code for the following paper. If you use this code or part of it, please cite:

Eduardo Fonseca, Diego Ortego, Kevin McGuinness, Noel E. O'Connor, Xavier Serra, "Unsupervised Contrastive Learning of Sound Event Representations", arXiv, 2020.

This repository contains a framework that comprises all the basic stages to learn an audio representation via unsupervised contrastive learning, and then evaluate the representation via supervised sound event classifcation. Please check our paper for more details. The system is implemented in PyTorch.

We're currently cleaning the code, which will be made available in the next few weeks. We will announce when it is available via twitter.

In the meantime, make sure to take a look at our paper!

Reference

@article{fonseca2020fsd50k,
  title={Unsupervised Contrastive Learning of Sound Event Representations},
  author={Fonseca, Eduardo and Ortego, Diego and McGuinness, Kevin and O'Connor, Noel E. and Serra, Xavier},
  journal={arXiv preprint arXiv},
  year={2020}
}