# The NES Music Database: A multi-instrumental dataset with expressive performance attributes

arXiv: https://arxiv.org/abs/1806.04278 · HTML: https://mlsanity.com/paper/1806.04278/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models](https://mlsanity.com/paper/2107.14653/) (2021)
- [YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations](https://mlsanity.com/paper/2211.07131/) (2022)
- [The GigaMIDI Dataset with Features for Expressive Music Performance Detection](https://mlsanity.com/paper/2502.17726/) (2025)
- [Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music](https://mlsanity.com/paper/2107.05916/) (2021)
- [The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos](https://mlsanity.com/paper/2404.04420/) (2024)
- [A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives](https://mlsanity.com/paper/2504.00837/) (2025)
- [A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives](https://mlsanity.com/paper/2210.13944/) (2022)
- [CoCoFormer: A controllable feature-rich polyphonic music generation method](https://mlsanity.com/paper/2310.09843/) (2023)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [Video-to-Music Generation for Gameplay Videos](https://mlsanity.com/paper/2609.31810/) (2026)

## Abstract (arXiv)

Existing research on music generation focuses on composition, but often ignores the expressive performance characteristics required for plausible renditions of resultant pieces. In this paper, we introduce the Nintendo Entertainment System Music Database (NES-MDB), a large corpus allowing for separate examination of the tasks of composition and performance. NES-MDB contains thousands of multi-instrumental songs composed for playback by the compositionally-constrained NES audio synthesizer. For each song, the dataset contains a musical score for four instrument voices as well as expressive attributes for the dynamics and timbre of each voice. Unlike datasets comprised of General MIDI files, NES-MDB includes all of the information needed to render exact acoustic performances of the original compositions. Alongside the dataset, we provide a tool that renders generated compositions as NES-style audio by emulating the device's audio processor. Additionally, we establish baselines for the tasks of composition, which consists of learning the semantics of composing for the NES synthesizer, and performance, which involves finding a mapping between a composition and realistic expressive attributes.