Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy
This addresses the challenge of accurately detecting and localizing overlapping sound events in various environments, which is incremental as it builds on existing neural network methods.
The paper tackled the problem of joint training degrading performance in polyphonic sound event detection and localization by proposing a two-stage method that first trains SED and then transfers learned features for DOA estimation, resulting in improved performance for both tasks on the DCASE 2019 Task 3 dataset.
Sound event detection (SED) and localization refer to recognizing sound events and estimating their spatial and temporal locations. Using neural networks has become the prevailing method for SED. In the area of sound localization, which is usually performed by estimating the direction of arrival (DOA), learning-based methods have recently been developed. In this paper, it is experimentally shown that the trained SED model is able to contribute to the direction of arrival estimation (DOAE). However, joint training of SED and DOAE degrades the performance of both. Based on these results, a two-stage polyphonic sound event detection and localization method is proposed. The method learns SED first, after which the learned feature layers are transferred for DOAE. It then uses the SED ground truth as a mask to train DOAE. The proposed method is evaluated on the DCASE 2019 Task 3 dataset, which contains different overlapping sound events in different environments. Experimental results show that the proposed method is able to improve the performance of both SED and DOAE, and also performs significantly better than the baseline method.