# Text-based LSTM networks for Automatic Music Composition

arXiv: https://arxiv.org/abs/1604.05358 · HTML: https://mlsanity.com/paper/1604.05358/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2016.

## Built on by (most cited first, 6 of 6)

- [TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method](https://mlsanity.com/paper/2109.09617/) (2021)
- [Lyapunov-Guided Representation of Recurrent Neural Network Performance](https://mlsanity.com/paper/2204.04876/) (2022)
- [Controllable Lyrics-to-Melody Generation](https://mlsanity.com/paper/2306.02613/) (2023)
- [Differential Music: Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals](https://mlsanity.com/paper/2108.10449/) (2021)
- [Everybody Compose: Deep Beats To Music](https://mlsanity.com/paper/2306.06284/) (2023)
- [Encoding of musical structures in hidden units of restricted Boltzmann machines](https://mlsanity.com/paper/2509.04899/) (2025)

## Abstract (arXiv)

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.