CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classification

TL;DR

This paper introduces CAA-Net, a novel CNN architecture with attention mechanisms designed for robust acoustic scene classification across multiple devices, providing both improved accuracy and interpretability of internal features.

Contribution

The paper proposes a conditional atrous CNN with attention for multi-device acoustic scene classification, incorporating a dual-branch structure and layer visualization for explainability.

Findings

Significantly improved performance on multi-device ASC dataset

Effective visualization of intermediate CNN layers

Enhanced robustness across different recording devices

Abstract

Acoustic Scene Classification (ASC) aims to classify the environment in which the audio signals are recorded. Recently, Convolutional Neural Networks (CNNs) have been successfully applied to ASC. However, the data distributions of the audio signals recorded with multiple devices are different. There has been little research on the training of robust neural networks on acoustic scene datasets recorded with multiple devices, and on explaining the operation of the internal layers of the neural networks. In this article, we focus on training and explaining device-robust CNNs on multi-device acoustic scene data. We propose conditional atrous CNNs with attention for multi-device ASC. Our proposed system contains an ASC branch and a device classification branch, both modelled by CNNs. We visualise and analyse the intermediate layers of the atrous CNNs. A time-frequency attention mechanism is employed to analyse the contribution of each time-frequency bin of the feature maps in the CNNs. On the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 ASC dataset, recorded with three devices, our proposed model performs significantly better than CNNs trained on single-device data.