Deep learning has rapidly become the state-of-the-art approach for music generation. However, training a deep model typically requires a large training set, which is often not available for specific musical styles. In this paper, we present augmentative generation (Aug-Gen), a method of dataset augmentation for any music generation system trained on a resource-constrained domain. The key intuition of this method is that the training data for a generative system can be augmented by examples the system produces during the course of training, provided these examples are of sufficiently high quality and variety. We apply Aug-Gen to Transformer-based chorale generation in the style of J.S. Bach, and show that this allows for longer training and results in better generative output.
- Pub Date:
- June 2020
- Computer Science - Sound;
- Computer Science - Machine Learning;
- Electrical Engineering and Systems Science - Audio and Speech Processing;
- Statistics - Machine Learning
- 2 pages, 2 figures, Machine Learning for Media Discovery (ML4MD) Workshop at ICML 2020