提出两种乐谱分块方式，提升多声部乐谱生成效果
Exploring Tokenization Methods for Multitrack Sheet Music Generation
- 用小节流和行流方式对乐谱分块，替代传统分块方法
- 小节流分块在生成效率和音乐性上均优于其他方法
- 适合音乐生成、人工智能作曲等研究者参考
本研究探索了在ABC记谱法中对多声部乐谱进行分词的方法，提出两种新策略：小节流分块（bar-stream patching）和行流分块（line-stream patching），并与现有的小节分块、字节分块及字节对编码（BPE）进行对比。实验结果表明，在计算效率与生成乐曲的音乐性方面，小节流分块整体表现最优，是多声部乐谱生成中极具前景的分词策略。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。