Sound Event Localization and Detection Using Activity-Coupled Cartesian DOA Vector and RD3net

Abstract

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.

arXiv commentSubmitted to DCASE2020 task3

References in corpus (6)

• WaveNet: A Generative Model for Raw Audio
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy
• Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection
• D3Net: Densely connected multidilated DenseNet for music source separation
• A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection

Cited by in corpus (6)

• A Survey of Sound Source Localization with Deep Learning Methods
• A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
• ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection
• An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection
• HumBugDB: A Large-scale Acoustic Mosquito Dataset
• ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization