Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

TL;DR

This paper explores using gated recurrent neural networks to generate and continue melodies, capturing long-range dependencies and style coherence in algorithmic music composition.

Contribution

It introduces a neural network model that processes rhythm and melody in parallel, effectively generating stylistically consistent melodies and continuations.

Findings

Successfully generated coherent melodies

Model captures long-range temporal dependencies

Able to suggest plausible continuations

Abstract

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated music composers able to generate new melodies coherent with the style they have been trained on. We employ gated recurrent unit networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two features. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.