Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation
This addresses the challenge of data scarcity for music generation in niche styles, though it is incremental as it builds on existing augmentation and generation techniques.
The paper tackles the problem of limited training data for music generation in specific styles by introducing augmentative generation (Aug-Gen), a dataset augmentation method that uses high-quality system outputs during training, resulting in improved generative output for Transformer-based chorale generation in the style of J.S. Bach.
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.