Exploring Tokenization Methods for Multitrack Sheet Music Generation

Autor:	Wang, Yashan, Wu, Shangda, Du, Xingjian, Sun, Maosong
Rok vydání:	2024
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: 3 pages, 1 figure, 1 table
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.17584 Zobrazit plný text záznamu View this record from Arxiv