Learning to Generate Music with BachProp
Florian Colombo, Johanni Brea, Wulfram Gerstner

TL;DR
BachProp is a deep learning algorithm capable of generating diverse musical scores by learning note transition probabilities, outperforming other models in capturing key features of various musical styles.
Contribution
The paper introduces BachProp, a novel music representation and deep network training method that generalizes music generation across multiple styles.
Findings
BachProp generates music that closely resembles original datasets.
It outperforms other models in capturing dataset features.
Qualitative comparisons show high musical quality.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic and Audio Processing · Music Technology and Sound Studies · Neuroscience and Music Perception
