Few-Shot Audio Classification with Attentional Graph Neural Networks

Shilei Zhang, Yong Qin, Kewei Sun, Yonghua Lin


Few-shot learning is a very promising and challenging field of machine learning as it aims to understand new concepts from very few labeled examples. In this paper, we propose attentional framework to extend recently proposed few-shot learning with graph neural network [1] in audio classification scenario. The objective of proposed attentional framework is to introduce a flexible framework to implement selectively concentration procedure on support examples for each query process. we also present an empirical study on confidence measure for few-shot learning application by combining posterior probability with normalized entropy of the network’s probability output. The efficiency of the proposed method is demonstrated with experiments on balanced training set of Audio set for training and a 5-way test set composed of about 5-hour audio data for testing.


 DOI: 10.21437/Interspeech.2019-1532

Cite as: Zhang, S., Qin, Y., Sun, K., Lin, Y. (2019) Few-Shot Audio Classification with Attentional Graph Neural Networks. Proc. Interspeech 2019, 3649-3653, DOI: 10.21437/Interspeech.2019-1532.


@inproceedings{Zhang2019,
  author={Shilei Zhang and Yong Qin and Kewei Sun and Yonghua Lin},
  title={{Few-Shot Audio Classification with Attentional Graph Neural Networks}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={3649--3653},
  doi={10.21437/Interspeech.2019-1532},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1532}
}