用新记谱法区分音乐是人写的还是AI生成的
Decoding Musical Origins: Distinguishing Human and AI Composers
- 用新记谱系统YNote将乐谱转为文本，用TF-IDF提取结构特征
- 模型准确率达98.25%，能识别不同生成方式的独有技术痕迹
- 适合内容溯源、版权鉴定和AI生成物检测的研究者使用
随着大语言模型快速发展，基于AI的音乐生成成为研究热点。然而，音乐数据表示仍是关键挑战。为此，本文提出一种新型机器学习友好型乐谱系统YNote。利用YNote，训练了一个分类模型，用于判断音乐是由人类（Native）、规则算法（Algorithm Generated）或大语言模型（LLM Generated）创作。研究将问题视为文本分类，采用词频-逆文档频率（TF-IDF）算法从YNote序列中提取结构特征，并使用合成少数类过采样技术（SMOTE）缓解数据不平衡问题。最终模型准确率达到98.25%，证明了YNote能有效保留风格信息。更重要的是，模型可识别不同AI生成技术留下的独特‘技术指纹’，为追踪AI生成内容来源提供了有力工具。
原文摘要 · Abstract (English)
With the rapid advancement of Large Language Models (LLMs), AI-driven music generation has become a vibrant and fruitful area of research. However, the representation of musical data remains a significant challenge. To address this, a novel, machine-learning-friendly music notation system, YNote, was developed. This study leverages YNote to train an effective classification model capable of distinguishing whether a piece of music was composed by a human (Native), a rule-based algorithm (Algorithm Generated), or an LLM (LLM Generated). We frame this as a text classification problem, applying the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to extract structural features from YNote sequences and using the Synthetic Minority Over-sampling Technique (SMOTE) to address data imbalance. The resulting model achieves an accuracy of 98.25%, successfully demonstrating that YNote retains sufficient stylistic information for analysis. More importantly, the model can identify the unique " technological fingerprints " left by different AI generation techniques, providing a powerful tool for tracing the origins of AI-generated content.
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。