A CNN Sound Classification Mechanism Using Data Augmentation
Sensors · 05.08.2023 · 23 (15) · 6972
DOI: 10.3390/s23156972 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.08.2023. Verfasst von Hung-Chi Chu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Engineering, Chaoyang University of Technology, Taichung 41349, Taiwan. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chaoyang University of Technology, Taiwan.
Abstract (Originalsprache)
Sound classification has been widely used in many fields. Unlike traditional signal-processing methods, using deep learning technology for sound classification is one of the most feasible and effective methods. However, limited by the quality of the training dataset, such as cost and resource constraints, data imbalance, and data annotation issues, the classification performance is affected. Therefore, we propose a sound classification mechanism based on convolutional neural networks and use the sound feature extraction method of Mel-Frequency Cepstral Coefficients (MFCCs) to convert sound signals into spectrograms. Spectrograms are suitable as input for CNN models. To provide the function of data augmentation, we can increase the number of spectrograms by setting the number of triangular bandpass filters. The experimental results show that there are 50 semantic categories in the ESC-50 dataset, the types are complex, and the amount of data is insufficient, resulting in a classification accuracy of only 63%. When using the proposed data augmentation method (K = 5), the accuracy is effectively increased to 97%. Furthermore, in the UrbanSound8K dataset, the amount of data is sufficient, so the classification accuracy can reach 90%, and the classification accuracy can be slightly increased to 92% via data augmentation. However, when only 50% of the training dataset is used, along with data augmentation, the establishment of the training model can be accelerated, and the classification accuracy can reach 91%.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information and Communication Engineering, Chaoyang University of Technology, Taichung 41349, Taiwan.
ORCID-Profile: Hung-Chi Chu
Förderung
- Chaoyang University of Technology, Taiwan
Zitieren
APA
Chu, H. C., Zhang, Y. L., & Chiang, H. C. (2023). A CNN Sound Classification Mechanism Using Data Augmentation. Sensors, 23(15), 6972. https://doi.org/10.3390/s23156972
Vancouver
Chu HC, Zhang YL, Chiang HC. A CNN Sound Classification Mechanism Using Data Augmentation. Sensors. 2023;23(15):6972. doi:10.3390/s23156972
BibTeX
@article{Chu2023,
author = {Chu, Hung-Chi and Zhang, Young-Lin and Chiang, Hao-Chu},
title = {A CNN Sound Classification Mechanism Using Data Augmentation},
journal = {Sensors},
year = {2023},
volume = {23},
number = {15},
pages = {6972},
doi = {10.3390/s23156972}
}
EUVIMED