Sound Event Localization and Detection Using Activity-Coupled Cartesian DOA Vector and RD3net
This work addresses sound event localization and detection for audio processing applications, presenting incremental improvements with novel method combinations.
The authors tackled sound event localization and detection (SELD) by proposing two systems: a single-stage approach using an activity-coupled Cartesian DOA vector (ACCDOA) representation and RD3Net architecture, and a two-stage alternative, achieving significant improvement over the baseline system.
Our systems submitted to the DCASE2020 task~3: Sound Event Localization and Detection (SELD) are described in this report. We consider two systems: a single-stage system that solve sound event localization~(SEL) and sound event detection~(SED) simultaneously, and a two-stage system that first handles the SED and SEL tasks individually and later combines those results. As the single-stage system, we propose a unified training framework that uses an activity-coupled Cartesian DOA vector~(ACCDOA) representation as a single target for both the SED and SEL tasks. To efficiently estimate sound event locations and activities, we further propose RD3Net, which incorporates recurrent and convolution layers with dense skip connections and dilation. To generalize the models, we apply three data augmentation techniques: equalized mixture data augmentation~(EMDA), rotation of first-order Ambisonic~(FOA) singals, and multichannel extension of SpecAugment. Our systems demonstrate a significant improvement over the baseline system.