Sound event detection using weakly-labeled semi-supervised data with GCRNNS, VAT and Self-Adaptive Label Refinement
This work addresses the problem of detecting sound events in domestic settings for applications like smart home systems, but it is incremental as it builds on existing methods for the DCASE challenge.
The paper tackled sound event detection in domestic environments using weakly-labeled semi-supervised data, achieving a macro averaged event-based F-score of 34.6%, which is a 20.5% relative improvement over the baseline.
In this paper, we present a gated convolutional recurrent neural network based approach to solve task 4, large-scale weakly labelled semi-supervised sound event detection in domestic environments, of the DCASE 2018 challenge. Gated linear units and a temporal attention layer are used to predict the onset and offset of sound events in 10s long audio clips. Whereby for training only weakly-labelled data is used. Virtual adversarial training is used for regularization, utilizing both labelled and unlabeled data. Furthermore, we introduce self-adaptive label refinement, a method which allows unsupervised adaption of our trained system to refine the accuracy of frame-level class predictions. The proposed system reaches an overall macro averaged event-based F-score of 34.6%, resulting in a relative improvement of 20.5% over the baseline system.