Calliope -- A Polyphonic Music Transformer

TL;DR

Calliope introduces a Transformer-based autoencoder that effectively models multi-track polyphonic music, significantly improving sequence reconstruction and generation, especially for long sequences, demonstrating the suitability of Transformers for complex musical data.

Contribution

The paper presents Calliope, a novel Transformer-based autoencoder specifically designed for efficient polyphonic music modeling, advancing the state of the art.

Findings

Improves sequence reconstruction accuracy.

Enhances music generation quality.

Performs well on long musical sequences.

Abstract

The polyphonic nature of music makes the application of deep learning to music modelling a challenging task. On the other hand, the Transformer architecture seems to be a good fit for this kind of data. In this work, we present Calliope, a novel autoencoder model based on Transformers for the efficient modelling of multi-track sequences of polyphonic music. The experiments show that our model is able to improve the state of the art on musical sequence reconstruction and generation, with remarkably good results especially on long sequences.