CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classification
This research provides a method for improving the robustness of acoustic scene classification models to different recording devices, which is a practical problem for real-world audio applications.
This paper addresses the challenge of device variability in Acoustic Scene Classification (ASC) by proposing a conditional atrous CNN with attention. The model significantly outperforms CNNs trained on single-device data on the DCASE 2018 ASC dataset, which includes recordings from three different devices.
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.