Text-based LSTM networks for Automatic Music Composition

Keunwoo Choi, George Fazekas, Mark Sandler
4/18/2016
cs.AIcs.MM

Official code: keunwoochoi/lstm_real_book (138 stars, last commit 2023-01-15). 1 more implementation below.

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.

View on arXivView PDF

Code Implementations(2)

keunwoochoi/lstm_real_bookOfficial100%

LSTM source code to generate jazz chord progressions

13819PythonFeb 18, 20163 years ago
keunwoochoi/LSTMetallicaOfficial100%

LSTM to generate drum tracks based on Metallica's midi drum tracks

10720PythonFeb 23, 20167 years ago

Similar Papers

Combinatorial music generation model with song structure graph analysis

83% match1 repo42023

Interactive Melody Generation System for Enhancing the Creativity of Musicians

83% match2024

Graph-based Polyphonic Multitrack Music Generation

82% match1 repo212023

An End-to-End Approach for Chord-Conditioned Song Generation

82% match2024

In-depth analysis of music structure as a text network

81% match2023

Controllable Lyrics-to-Melody Generation

81% match2023

Cite this paper

@article{choi2016textbased,
  title  = {Text-based LSTM networks for Automatic Music Composition},
  author = {Keunwoo Choi and George Fazekas and Mark Sandler},
  year   = {2016},
  eprint = {1604.05358},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1604.05358}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1604.05358.svg)](https://codeofpaper.com/paper/1604.05358)

Discussion