EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation
arXiv:2104.07326
Abstract
The research in Environmental Sound Classification (ESC) has been progressively growing with the emergence of deep learning algorithms. However, data scarcity poses a major hurdle for any huge advance in this domain. Data augmentation offers an excellent solution to this problem. While Generative Adversarial Networks (GANs) have been successful in generating synthetic speech and sounds of musical instruments, they have hardly been applied to the generation of environmental sounds. This paper presents EnvGAN, the first ever application of GANs for the adversarial generation of environmental sounds. Our experiments on three standard ESC datasets illustrate that the EnvGAN can synthesize audio similar to the ones in the datasets. The suggested method of augmentation outshines most of the futuristic techniques for audio augmentation.
arXiv commentSubmitted to IEEE Transactions on Audio, Speech and Language Processing
References in corpus (5)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings
- Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning
- A multi-device dataset for urban acoustic scene classification