Learning to Generate Music with BachProp
This work addresses the need for flexible music composition algorithms that can handle diverse musical structures, though it appears incremental in improving upon existing methods.
The authors tackled the problem of generating music scores across various styles by introducing BachProp, a deep learning model that uses a novel music representation to predict note transitions, and demonstrated it captures dataset features better than other models.
As deep learning advances, 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 many styles given sufficient training data. To adapt BachProp to a broad range of musical styles, we propose a novel 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 generated by BachProp are compared with the original corpora as well as with different network architectures and other related models. We show that BachProp captures important features of the original datasets better than other models and invite the reader to a qualitative comparison on a large collection of generated songs.