Skip to main content
Imposing Higher-Level Structure in Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines and Constraints

Abstract

We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative model is combined with gradient des- cent constraint optimisation to provide further control over the genera- tion process. Among other things, this allows for the use of a “template” piece, from which some structural properties can be extracted, and trans- ferred as constraints to the newly generated material. The sampling pro- cess is guided with Simulated Annealing to avoid local optima, and to find solutions that both satisfy the constraints, and are relatively stable with respect to the C-RBM. Results show that with this approach it is possible to control the higher-level self-similarity structure, the meter, and the tonal properties of the resulting musical piece, while preserving its local musical coherence.

How to Cite

Lattner, S., Grachten, M. & Widmer, G., (2018) “Imposing Higher-Level Structure in Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines and Constraints”, Journal of Creative Music Systems 2(2). doi: https://doi.org/10.5920/jcms.2018.01

Downloads

Download PDF

1187

Views

984

Downloads

1

Citations

Share

Authors

Stefan Lattner (Johannes Kepler University)
Maarten Grachten (Austrian Research Institute for Artificial Intelligence)
Gerhard Widmer (Johannes Kepler University)

Downloads

Issue

Publication details

Licence

Creative Commons Attribution 4.0

Identifiers

Peer Review

This article has been peer reviewed.

File Checksums (MD5)

  • PDF: 54b7b2ad38632286310da611f16487b0