# Do we need more complex representations for structure? A comparison of note duration representation for Music Transformers

arXiv: https://arxiv.org/abs/2410.10515 · HTML: https://mlsanity.com/paper/2410.10515/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures](https://mlsanity.com/paper/2008.01307/) (2020)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [Multitrack Music Transformer](https://mlsanity.com/paper/2207.06983/) (2022)
- [Quantifying Musical Style: Ranking Symbolic Music based on Similarity to a Style](https://mlsanity.com/paper/2003.06226/) (2020)
- [Impact of time and note duration tokenizations on deep learning symbolic music modeling](https://mlsanity.com/paper/2310.08497/) (2023)

## Abstract (arXiv)

In recent years, deep learning has achieved formidable results in creative computing. When it comes to music, one viable model for music generation are Transformer based models. However, while transformers models are popular for music generation, they often rely on annotated structural information. In this work, we inquire if the off-the-shelf Music Transformer models perform just as well on structural similarity metrics using only unannotated MIDI information. We show that a slight tweak to the most common representation yields small but significant improvements. We also advocate that searching for better unannotated musical representations is more cost-effective than producing large amounts of curated and annotated data.