English

Learning generic feature representation with synthetic data for weakly-supervised sound event detection by inter-frame distance loss

Sound 2020-11-03 v1 Audio and Speech Processing

Abstract

Due to the limitation of strong-labeled sound event detection data set, using synthetic data to improve the sound event detection system performance has been a new research focus. In this paper, we try to exploit the usage of synthetic data to improve the feature representation. Based on metric learning, we proposed inter-frame distance loss function for domain adaptation, and prove the effectiveness of it on sound event detection. We also applied multi-task learning with synthetic data. We find the the best performance can be achieved when the two methods being used together. The experiment on DCASE 2018 task 4 test set and DCASE 2019 task 4 synthetic set both show competitive results.

Keywords

Cite

@article{arxiv.2011.00695,
  title  = {Learning generic feature representation with synthetic data for weakly-supervised sound event detection by inter-frame distance loss},
  author = {Yuxin Huang and Liwei Lin and Xiangdong Wang and Hong Liu and Yueliang Qian and Min Liu and Kazushige Ouchi},
  journal= {arXiv preprint arXiv:2011.00695},
  year   = {2020}
}
R2 v1 2026-06-23T19:49:51.944Z