# ComMU: Dataset for Combinatorial Music Generation

arXiv: https://arxiv.org/abs/2211.09385 · HTML: https://mlsanity.com/paper/2211.09385/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation](https://mlsanity.com/paper/1703.10847/) (2017)
- [Video Background Music Generation with Controllable Music Transformer](https://mlsanity.com/paper/2111.08380/) (2021)
- [LakhNES: Improving multi-instrumental music generation with cross-domain pre-training](https://mlsanity.com/paper/1907.04868/) (2019)
- [The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures](https://mlsanity.com/paper/2008.01307/) (2020)
- [EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation](https://mlsanity.com/paper/2108.01374/) (2021)
- [MMM : Exploring Conditional Multi-Track Music Generation with the Transformer](https://mlsanity.com/paper/2008.06048/) (2020)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music](https://mlsanity.com/paper/2010.07061/) (2020)
- [Computer-Generated Music for Tabletop Role-Playing Games](https://mlsanity.com/paper/2008.07009/) (2020)
- [A Unit Selection Methodology for Music Generation Using Deep Neural Networks](https://mlsanity.com/paper/1612.03789/) (2016)
- [Generation of musical patterns through operads](https://mlsanity.com/paper/2104.12432/) (2021)

## Built on by (most cited first, 8 of 8)

- [Mousai: Text-to-Music Generation with Long-Context Latent Diffusion](https://mlsanity.com/paper/2301.11757/) (2023)
- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)
- [The GigaMIDI Dataset with Features for Expressive Music Performance Detection](https://mlsanity.com/paper/2502.17726/) (2025)
- [FilmComposer: LLM-Driven Music Production for Silent Film Clips](https://mlsanity.com/paper/2503.08147/) (2025)
- [Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes](https://mlsanity.com/paper/2505.15559/) (2025)
- [MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage](https://mlsanity.com/paper/2403.10024/) (2024)
- [Combinatorial music generation model with song structure graph analysis](https://mlsanity.com/paper/2312.15400/) (2023)
- [How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness](https://mlsanity.com/paper/2608.18025/) (2026)

## Abstract (arXiv)

Commercial adoption of automatic music composition requires the capability of generating diverse and high-quality music suitable for the desired context (e.g., music for romantic movies, action games, restaurants, etc.). In this paper, we introduce combinatorial music generation, a new task to create varying background music based on given conditions. Combinatorial music generation creates short samples of music with rich musical metadata, and combines them to produce a complete music. In addition, we introduce ComMU, the first symbolic music dataset consisting of short music samples and their corresponding 12 musical metadata for combinatorial music generation. Notable properties of ComMU are that (1) dataset is manually constructed by professional composers with an objective guideline that induces regularity, and (2) it has 12 musical metadata that embraces composers' intentions. Our results show that we can generate diverse high-quality music only with metadata, and that our unique metadata such as track-role and extended chord quality improves the capacity of the automatic composition. We highly recommend watching our video before reading the paper (https://pozalabs.github.io/ComMU).