Data Augmentation Using Generative Adversarial Network for Environmental Sound Classification
Autor: | Suresh Kumaraswamy, Aswathy Madhu |
---|---|
Rok vydání: | 2019 |
Předmět: |
Computer science
business.industry Deep learning Principal (computer security) 020206 networking & telecommunications 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Synthetic data 0202 electrical engineering electronic engineering information engineering Environmental sound classification 020201 artificial intelligence & image processing Artificial intelligence business computer Generative adversarial network |
Zdroj: | EUSIPCO |
DOI: | 10.23919/eusipco.2019.8902819 |
Popis: | Various types of deep learning architecture have been steadily gaining impetus for automatic environmental sound classification. However, the relative paucity of publicly accessible dataset hinders any further improvement in this direction. This work has two principal contributions. First, we put forward a deep learning framework employing convolutional neural network for automatic environmental sound classification. Second, we investigate the possibility of generating synthetic data using data augmentation. We suggest a novel technique for audio data augmentation using a generative adversarial network (GAN). The proposed model along with data augmentation is assessed on the UrbanSound8K dataset. The results authenticate that the suggested method surpasses state-of-the-art methods for data augmentation. |
Databáze: | OpenAIRE |
Externí odkaz: |