# Exploring Tokenization Methods for Multitrack Sheet Music Generation

arXiv: https://arxiv.org/abs/2410.17584 · HTML: https://mlsanity.com/paper/2410.17584/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [Music transcription modelling and composition using deep learning](https://mlsanity.com/paper/1604.08723/) (2016)
- [MuPT: A Generative Symbolic Music Pretrained Transformer](https://mlsanity.com/paper/2404.06393/) (2024)
- [Beyond Language Models: Byte Models are Digital World Simulators](https://mlsanity.com/paper/2402.19155/) (2024)
- [TunesFormer: Forming Irish Tunes with Control Codes by Bar Patching](https://mlsanity.com/paper/2301.02884/) (2023)
- [CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models](https://mlsanity.com/paper/2410.13267/) (2024)

## Built on by (most cited first, 3 of 3)

- [NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms](https://mlsanity.com/paper/2502.18008/) (2025)
- [Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation](https://mlsanity.com/paper/2508.01394/) (2025)
- [Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation](https://mlsanity.com/paper/2608.03999/) (2026)

## Abstract (arXiv)

This study explores the tokenization of multitrack sheet music in ABC notation, introducing two methods--bar-stream and line-stream patching. We compare these methods against existing techniques, including bar patching, byte patching, and Byte Pair Encoding (BPE). In terms of both computational efficiency and the musicality of the generated compositions, experimental results show that bar-stream patching performs best overall compared to the others, which makes it a promising tokenization strategy for sheet music generation.