Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
Abstract
In this technical report, we present a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge. Task 1 comprises two different sub-tasks: (i) Task 1a focuses on ASC of audio signals recorded with multiple (real and simulated) devices into ten different fine-grained classes, and (ii) Task 1b concerns with classification of data into three higher-level classes using low-complexity solutions. For Task 1a, we propose a novel two-stage ASC system leveraging upon ad-hoc score combination of two convolutional neural networks (CNNs), classifying the acoustic input according to three classes, and then ten classes, respectively. Four different CNN-based architectures are explored to implement the two-stage classifiers, and several data augmentation techniques are also investigated. For Task 1b, we leverage upon a quantization method to reduce the complexity of two of our top-accuracy three-classes CNN-based architectures. On Task 1a development data set, an ASC accuracy of 76.9\% is attained using our best single classifier and data augmentation. An accuracy of 81.9\% is then attained by a final model fusion of our two-stage ASC classifiers. On Task 1b development data set, we achieve an accuracy of 96.7\% with a model size smaller than 500KB. Code is available: https://github.com/MihawkHu/DCASE2020_task1.
Keywords
Cite
@article{arxiv.2007.08389,
title = {Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation},
author = {Hu Hu and Chao-Han Huck Yang and Xianjun Xia and Xue Bai and Xin Tang and Yajian Wang and Shutong Niu and Li Chai and Juanjuan Li and Hongning Zhu and Feng Bao and Yuanjun Zhao and Sabato Marco Siniscalchi and Yannan Wang and Jun Du and Chin-Hui Lee},
journal= {arXiv preprint arXiv:2007.08389},
year = {2020}
}
Comments
Revised Technical Report. Proposed systems attain 2nds in both Task-1a and Task-1b in the official DCASE challenge 2020