发表机构
University of California, San Diego; University of Michigan, Ann Arbor（加利福尼亚大学圣迭戈分校; 密歇根大学安娜堡分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出MusPyExpress扩展MusPy库，支持提取表情文本，解析PDMX数据集展示相关数据丰富性，并开展三类利用该信息的生成任务以推动符号音乐建模。
AI 中文摘要
当前符号音乐建模工作主要依赖从类MIDI数据中提取的表示形式。这类格式虽能将符号音乐建模为音符序列，但遗漏了西方乐谱中常见的大量符号注释，即通常所称的表情文本，如速度或力度，这些注释规定了音乐作品及演奏中与时间、速度相关的控制项。为缓解这一差距，我们提出MusPyExpress，这是流行的符号音乐处理库MusPy的扩展，可提取表情文本与符号音乐一同用于下游建模。利用该扩展，我们解析PDMX数据集以展示MusicXML数据集中可用的表情文本的丰富性。此外，我们引入多个生成任务，包括表情-音符联合生成、表情条件音乐生成及表情标注，这些任务均利用了额外的符号信息。
英文摘要
Current work in modeling symbolic music primarily relies on representations extracted from MIDI-like data. While such formats allow for modeling symbolic music as sequences of notes, they omit the large space of symbolic annotations common in western sheet music broadly known as expression text, such as tempo or dynamics, which specify time- and velocity-dependent controls on the musical composition and performance. To alleviate this gap, we present MusPyExpress, an extension to the popular symbolic music processing library MusPy that enables the extraction of expression text along with symbolic music for downstream modeling. Utilizing this extension, we parse the PDMX dataset to illustrate the wealth of expression text available in MusicXML datasets. Additionally, we introduce multiple generative tasks, including joint expression-note generation, expression-conditioned music generation, and expression tagging, that take advantage of this additional notational information.
CommentsAccepted at NeurIPS 2025 Workshop on AI for Music: Where Creativity Meets Computation; 10 pages, 6 figures
