A Two-Stage Approach to Device-Robust Acoustic Scene Classification
Abstract
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage system leverages on an ad-hoc score combination based on two CNN classifiers: (i) the first CNN classifies acoustic inputs into one of three broad classes, and (ii) the second CNN classifies the same inputs into one of ten finer-grained classes. Three different CNN architectures are explored to implement the two-stage classifiers, and a frequency sub-sampling scheme is investigated. Moreover, novel data augmentation schemes for ASC are also investigated. Evaluated on DCASE 2020 Task 1a, our results show that the proposed ASC system attains a state-of-the-art accuracy on the development set, where our best system, a two-stage fusion of CNN ensembles, delivers a 81.9% average accuracy among multi-device test data, and it obtains a significant improvement on unseen devices. Finally, neural saliency analysis with class activation mapping (CAM) gives new insights on the patterns learnt by our models.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2020
- DOI:
- 10.48550/arXiv.2011.01447
- arXiv:
- arXiv:2011.01447
- Bibcode:
- 2020arXiv201101447H
- Keywords:
-
- Computer Science - Sound;
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing;
- Electrical Engineering and Systems Science - Audio and Speech Processing
- E-Print:
- Submitted to ICASSP 2021. Code available: https://github.com/MihawkHu/DCASE2020_task1