# Differential Music: Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals

arXiv: https://arxiv.org/abs/2108.10449 · HTML: https://mlsanity.com/paper/2108.10449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [DeepBach: a Steerable Model for Bach Chorales Generation](https://mlsanity.com/paper/1612.01010/) (2016)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [Music transcription modelling and composition using deep learning](https://mlsanity.com/paper/1604.08723/) (2016)
- [Text-based LSTM networks for Automatic Music Composition](https://mlsanity.com/paper/1604.05358/) (2016)
- [Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning](https://mlsanity.com/paper/1902.01973/) (2019)

## Abstract (arXiv)

This paper presents a generative AI model for automated music composition with LSTM networks that takes a novel approach at encoding musical information which is based on movement in music rather than absolute pitch. Melodies are encoded as a series of intervals rather than a series of pitches, and chords are encoded as the set of intervals that each chord note makes with the melody at each timestep. Experimental results show promise as they sound musical and tonal. There are also weaknesses to this method, mainly excessive modulations in the compositions, but that is expected from the nature of the encoding. This issue is discussed later in the paper and is a potential topic for future work.