# Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1606.07251 · HTML: https://mlsanity.com/paper/1606.07251/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2016.

## Built on by (most cited first, 4 of 4)

- [Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure](https://mlsanity.com/paper/2102.09794/) (2021)
- [Is Disentanglement enough? On Latent Representations for Controllable Music Generation](https://mlsanity.com/paper/2108.01450/) (2021)
- [Melody Infilling with User-Provided Structural Context](https://mlsanity.com/paper/2210.02829/) (2022)
- [Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI](https://mlsanity.com/paper/2311.08336/) (2023)

## Abstract (arXiv)

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.