Text-based LSTM networks for Automatic Music Composition
Artificial Intelligence
2016-04-20 v1 Multimedia
Abstract
In this paper, we introduce new methods and discuss results of text-based LSTM (Long Short-Term Memory) networks for automatic music composition. The proposed network is designed to learn relationships within text documents that represent chord progressions and drum tracks in two case studies. In the experiments, word-RNNs (Recurrent Neural Networks) show good results for both cases, while character-based RNNs (char-RNNs) only succeed to learn chord progressions. The proposed system can be used for fully automatic composition or as semi-automatic systems that help humans to compose music by controlling a diversity parameter of the model.
Cite
@article{arxiv.1604.05358,
title = {Text-based LSTM networks for Automatic Music Composition},
author = {Keunwoo Choi and George Fazekas and Mark Sandler},
journal= {arXiv preprint arXiv:1604.05358},
year = {2016}
}
Comments
Accepted in the 1st Conference on Computer Simulation of Musical Creativity, 2016