Sound Source Detection, Localization and Classification using Consecutive Ensemble of CRNN Models
Sławomir Kapka, Mateusz Lewandowski · 2019
In this paper, we describe our method for DCASE2019 task 3: Sound Event Localization and Detection (SELD).We use four CRNN SELDnet-like single output models which run in a consecutive manner to recover all possible information of occurring events.We decompose the SELD task into estimating number of active sources, estimating direction of arrival of a single source, estimating direction of arrival of the second source where the direction of the first one is known and a multi-label classification task.We use custom consecutive ensemble to predict events' onset, offset, direction of arrival and class.The proposed approach is evaluated on the TAU Spatial Sound Events 2019 -Ambisonic and it is compared with other participants' submissions.