Learning How to Listen: A Temporal-Frequential Attention Model for Sound Event Detection

Yu-Han Shen, Ke-Xin He, Wei-Qiang Zhang


In this paper, we propose a temporal-frequential attention model for sound event detection (SED). Our network learns how to listen with two attention models: a temporal attention model and a frequential attention model. Proposed system learns when to listen using the temporal attention model while it learns where to listen on the frequency axis using the frequential attention model. With these two models, we attempt to make our system pay more attention to important frames or segments and important frequency components for sound event detection. Our proposed method is demonstrated on the task 2 of Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 Challenge and outperforms state-of-the-art methods.


 DOI: 10.21437/Interspeech.2019-2045

Cite as: Shen, Y., He, K., Zhang, W. (2019) Learning How to Listen: A Temporal-Frequential Attention Model for Sound Event Detection. Proc. Interspeech 2019, 2563-2567, DOI: 10.21437/Interspeech.2019-2045.


@inproceedings{Shen2019,
  author={Yu-Han Shen and Ke-Xin He and Wei-Qiang Zhang},
  title={{Learning How to Listen: A Temporal-Frequential Attention Model for Sound Event Detection}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={2563--2567},
  doi={10.21437/Interspeech.2019-2045},
  url={http://dx.doi.org/10.21437/Interspeech.2019-2045}
}