# Coupled Recurrent Models for Polyphonic Music Composition

arXiv: https://arxiv.org/abs/1811.08045 · HTML: https://mlsanity.com/paper/1811.08045/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [Anticipatory Music Transformer](https://mlsanity.com/paper/2306.08620/) (2023)
- [Tokyo Kion-On: Query-Based Generative Sonification of Atmospheric Data](https://mlsanity.com/paper/2208.02494/) (2022)

## Abstract (arXiv)

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.