Exploring Tokenization Methods for Multitrack Sheet Music Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yashan, Wu, Shangda, Du, Xingjian, Sun, Maosong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908100673404928
author Wang, Yashan
Wu, Shangda
Du, Xingjian
Sun, Maosong
author_facet Wang, Yashan
Wu, Shangda
Du, Xingjian
Sun, Maosong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Tokenization Methods for Multitrack Sheet Music Generation
Wang, Yashan
Wu, Shangda
Du, Xingjian
Sun, Maosong
Sound
Artificial Intelligence
Audio and Speech Processing
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.
title Exploring Tokenization Methods for Multitrack Sheet Music Generation
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2410.17584