BachProp: Learning to Compose Music in Multiple Styles
This addresses the need for flexible music composition algorithms that can handle diverse styles, though it appears incremental as it builds on existing deep learning approaches.
The authors tackled the problem of generating music scores in multiple styles by introducing BachProp, which uses a normalized music representation and deep learning to predict note transitions, and found through crowdsourcing that its generated scores were not less preferred than the original training corpora.
Hand in hand with deep learning advancements, algorithms of music composition increase in performance. However, most of the successful models are designed for specific musical structures. Here, we present BachProp, an algorithmic composer that can generate music scores in any style given sufficient training data. To adapt BachProp to a broad range of musical styles, we propose a novel normalized representation of music and train a deep network to predict the note transition probabilities of a given music corpus. In this paper, new music scores sampled by BachProp are compared with the original corpora via crowdsourcing. This evaluation indicates that the music scores generated by BachProp are not less preferred than the original music corpus the algorithm was provided with.