Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

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.

Published in:
Proceedings of the 1st Conference on Computer Simulation of Musical Creativity
Presented at:
1st Conference on Computer Simulation of Musical Creativity, University of Huddersfield, UK, 17 – 19 June 2016

 Record created 2016-08-29, last modified 2019-03-17

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)