Guided Learning Convolution System for DCASE 2019 Task 4
|Citation:||L. Lin, X. Wang, H. Liu & Y. Qian, "Guided Learning Convolution System for DCASE 2019 Task 4", Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), pages 134–138, New York University, NY, USA, Oct. 2019|
|Abstract:||In this paper, we describe in detail the system we submitted to DCASE2019 task 4: sound event detection (SED) in domestic environments. We approach SED as a multiple instance learning (MIL) problem and employ a convolutional neural network (CNN) with class-wise attention pooling (cATP) module to solve it. By considering the interference caused by the co-occurrence of multiple events in the unbalanced dataset, we combine the cATP-MIL framework with the Disentangled Feature. To take advantage of the unlabeled data, we adopt Guided Learning for semi-supervised learning. A group of median filters with adaptive window sizes is utilized in post-processing. We also analyze the effect of the synthetic data on the performance of the model and finally achieve an event-based F-measure of 45.43% on the validation set and an event-based F-measure of 42.7% on the test set. The system we submitted to the challenge achieves the best performance compared to those of other participants.|
|Appears in Collections:||Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)|
Files in This Item:
|DCASE2019Workshop_Lin_16.pdf||896.04 kB||Adobe PDF||View/Open|
Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.