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

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.

5 pages

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
• A multi-device dataset for urban acoustic scene classification
• SONYC: A System for the Monitoring, Analysis and Mitigation of Urban Noise Pollution

Cited by in corpus (12)

• Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019
• Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy
• PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
• Acoustic Scene Classification with Squeeze-Excitation Residual Networks
• Acoustic Scene Classification with Spectrogram Processing Strategies
• Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization
• Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification
• An Ontology-Aware Framework for Audio Event Classification
• Non-Negative Matrix Factorization-Convolutional Neural Network (NMF-CNN) For Sound Event Detection
• Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study
• Source separation with weakly labelled data: An approach to computational auditory scene analysis
• Semi-Supervised NMF-CNN For Sound Event Detection