Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification
Authors:
Top Cited Papers
Open Access
- 23 January 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (3) , 279-283
Abstract
The ability of deep convolutional neural networks (CNNs) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family of high-capacity models. This study has two primary contributions: first, we propose a deep CNN architecture for environmental sound classification. Second, we propose the use of audio data augmentation for overcoming the problem of data scarcity and explore the influence of different augmentations on the performance of the proposed CNN architecture. Combined with data augmentation, the proposed model produces state-of-the-art results for environmental sound classification. We show that the improved performance stems from the combination of a deep, high-capacity model and an augmented training set: this combination outperforms both the proposed CNN without augmentation and a “shallow” dictionary learning model with augmentation. Finally, we examine the influence of each augmentation on the model's classification accuracy for each class, and observe that the accuracy for each class is influenced differently by each augmentation, suggesting that the performance of the model could be improved further by applying class-conditional data augmentation.Keywords
All Related Versions
Funding Information
- NSF (1544753)
This publication has 23 references indexed in Scilit:
- Automatic Environmental Sound Recognition: Performance Versus Computational CostIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- ESC2015
- Environmental sound classification with convolutional neural networks2015
- Polyphonic sound event detection using multi label deep neural networks2015
- Detection and Classification of Acoustic Scenes and EventsIEEE Transactions on Multimedia, 2015
- Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations2015
- A Dataset and Taxonomy for Urban Sound Research2014
- Detection and classification of acoustic scenes and events: An IEEE AASP challenge2013
- Spectral vs. spectro-temporal features for acoustic event detection2011
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998