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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414835 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Acoustic scene classification, robustness, convolutional neural networks, data augmentation, class activation mapping | Conference | 0 |
PageRank | References | Authors |
0.34 | 7 | 16 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hu Hu | 1 | 2 | 0.69 |
Chao-Han Huck Yang | 2 | 0 | 1.69 |
Xianjun Xia | 3 | 12 | 3.02 |
Xue Bai | 4 | 119 | 14.75 |
Xin Tang | 5 | 0 | 0.68 |
Yajian Wang | 6 | 0 | 0.34 |
Shutong Niu | 7 | 0 | 0.68 |
Li Chai | 8 | 80 | 22.25 |
Juanjuan Li | 9 | 0 | 0.34 |
Hongning Zhu | 10 | 0 | 0.34 |
Feng Bao | 11 | 0 | 0.34 |
Yuanjun Zhao | 12 | 14 | 6.42 |
Sabato Marco Siniscalchi | 13 | 310 | 30.21 |
Yannan Wang | 14 | 7 | 5.71 |
Qing-Feng LIU | 15 | 172 | 22.25 |
Chin-Hui Lee | 16 | 6101 | 852.71 |