Exploring Tokenization Methods for Multitrack Sheet Music Generation
Yashan Wang, Shangda Wu, Xingjian Du, Maosong Sun

TL;DR
This paper investigates different tokenization strategies for multitrack sheet music in ABC notation, finding that bar-stream patching offers the best balance of efficiency and musical quality in generated compositions.
Contribution
It introduces two novel tokenization methods—bar-stream and line-stream patching—and compares them with existing techniques, highlighting bar-stream patching as the most effective.
Findings
Bar-stream patching outperforms other methods in efficiency.
Bar-stream patching produces more musically coherent compositions.
The study provides a comparative analysis of tokenization techniques for sheet music generation.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic Technology and Sound Studies · Music and Audio Processing · Computer Graphics and Visualization Techniques
MethodsApproximate Bayesian Computation · Activation Patching
