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