用4个字符简化乐谱，让大模型更高效生成音乐。
YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation
- 用四个字符定义音符与音高，格式固定易读。
- 仅用两个音符作提示，生成音乐风格一致且连贯。
- 适合想用大模型做音乐生成的研究者或创作者。
使用大型语言模型（LLMs）进行音乐生成的研究快速发展，但现有乐谱系统如MIDI、ABC Notation和MusicXML仍过于复杂，难以有效用于微调LLMs。这些格式因结构复杂且不一致，对机器和人类都难解析。为此，我们提出YNote，一种仅用四个字符表示音符及其音高的简化乐谱系统。该格式固定，保证一致性，便于读取，更适合用于微调LLMs。实验中，我们在YNote编码的数据集上微调了GPT-2（124M），BLEU和ROUGE得分分别达到0.883和0.766。仅以两个音符为提示，模型即可生成连贯且风格匹配的音乐。我们认为YNote为机器学习应用提供了比现有乐谱更实用的替代方案，有望显著提升基于LLMs的音乐生成质量。
原文摘要 · Abstract (English)
The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote's fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs.
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。