Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems

TL;DR

This paper presents generic CNN-based baseline systems for multiple audio recognition tasks in the DCASE 2019 challenge, demonstrating that a 9-layer CNN with average pooling performs well across diverse tasks.

Contribution

It introduces cross-task CNN baseline systems for various audio recognition challenges, analyzing their performance without task-specific modifications.

Findings

9-layer CNN with average pooling is effective for most tasks

Optimal CNN architecture varies depending on the task

Baseline systems provide a common framework for different audio tasks

Abstract

The Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge focuses on audio tagging, sound event detection and spatial localisation. DCASE 2019 consists of five tasks: 1) acoustic scene classification, 2) audio tagging with noisy labels and minimal supervision, 3) sound event localisation and detection, 4) sound event detection in domestic environments, and 5) urban sound tagging. In this paper, we propose generic cross-task baseline systems based on convolutional neural networks (CNNs). The motivation is to investigate the performance of a variety of models across several audio recognition tasks without exploiting the specific characteristics of the tasks. We looked at CNNs with 5, 9, and 13 layers, and found that the optimal architecture is task-dependent. For the systems we considered, we found that the 9-layer CNN with average pooling after convolutional layers is a good model for a majority of the DCASE 2019 tasks.