Coupled Recurrent Models for Polyphonic Music Composition
Sound
2019-11-28 v2 Machine Learning
Audio and Speech Processing
Machine Learning
Abstract
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distributions, we borrow ideas from both convolutional and recurrent neural models; we argue that these ideas are natural for capturing music's pitch invariances, temporal structure, and polyphony. We train models for single-voice and multi-voice composition on 2,300 scores from the KernScores dataset.
Cite
@article{arxiv.1811.08045,
title = {Coupled Recurrent Models for Polyphonic Music Composition},
author = {John Thickstun and Zaid Harchaoui and Dean P. Foster and Sham M. Kakade},
journal= {arXiv preprint arXiv:1811.08045},
year = {2019}
}
Comments
13 pages; long version of the paper appearing in ISMIR 2019