Onsets, Activity, and Events: A Multi-task Approach for Polyphonic Sound Event Modelling
|Citation:||A. Pankajakshan, H. Bear & E. Benetos, "Onsets, Activity, and Events: A Multi-task Approach for Polyphonic Sound Event Modelling", Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), pages 174–178, New York University, NY, USA, Oct. 2019|
|Abstract:||State of the art polyphonic sound event detection (SED) systems function as frame-level multi-label classification models. In the context of dynamic polyphony levels at each frame, sound events interfere with each other which degrade a classifier’s ability to learn the exact frequency profile of individual sound events. Frame-level localized classifiers also fail to explicitly model the long-term temporal structure of sound events. Consequently, the event-wise detection performance is less than the segment-wise detection. We define ‘temporally precise polyphonic sound event detection’ as the subtask of detecting sound event instances with the correct onset. Here, we investigate the effectiveness of sound activity detection (SAD) and onset detection as auxiliary tasks to improve temporal precision in polyphonic SED using multi-task learning. SAD helps to differentiate event activity frames from noisy and silence frames and helps to avoid missed detections at each frame. Onset predictions ensure the start of each event which in turn are used to condition predictions of both SAD and SED. Our experiments on the URBAN-SED dataset show that by conditioning SED with onset detection and SAD, there is over a three-fold relative improvement in event-based F -score.|
|Appears in Collections:||Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)|
Files in This Item:
|DCASE2019Workshop_Pankajakshan_43.pdf||597.71 kB||Adobe PDF||View/Open|
Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.