Combining Multi-Scale Features Using Sample-level Deep Convolutional Neural Networks for Weakly Supervised Sound Event Detection

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 261
  • Download : 0
This paper describes our method submitted to large-scale weakly supervised sound event detection for smart cars in the DCASE Challenge 2017. It is based on two deep neural network methods suggested for music auto-tagging. One is training sample-level Deep Convolutional Neural Networks (DCNN) using raw waveforms as a feature extractor. The other is aggregating features on multi-scaled models of the DCNNs and making final predictions from them. With this approach, we achieved the best results, 47.3% in F-score on subtask A (audio tagging) and 0.75 in error rate on subtask B (sound event detection) in the evaluation. These results show that the waveform-based models can be comparable to spectrogram-based models when compared to other DCASE Task 4 submissions. Finally, we visualize hierarchically learned filters from the challenge dataset in each layer of the waveform-based model to explain how they discriminate the events.
Publisher
IEEE
Issue Date
2017-11-17
Language
English
Citation

Proceedings of the 2nd Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)

URI
http://hdl.handle.net/10203/239538
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0