提出五维诊断框架，精准定位AI翻唱中的音乐错误。
A Diagnostic Evaluation Framework for AI-Generated Cover Songs Using Music-Theoretic and Acoustic Features
- 构建旋律、和声、调性等五个维度的诊断体系
- 和声与编排错误率高达53%和47%，调性相对稳定
- 适合音乐生成质量评估与缺陷分析的研究者
AI生成的翻唱常因局部音乐错误而失败，全局质量评分难以定位问题：例如人声轮廓仍可辨识，但伴奏使用了错误和声功能，或整体保持在调内但编排不完整。本文提出一个包含旋律音高、和声进行、调性一致性、风格一致性和编排/制作质量的五维诊断框架。基准数据集包含由6个系统从5首原曲生成的30首翻唱作品，配有专家严重程度评分及9个符号化或声学特征。结果显示，和声进行与编排错误率最高（分别为53%和47%），而调性一致性较好；有6首作品虽调性合理，却存在严重和声错误。大跳比例与旋律评分呈弱相关（Spearman rho = -0.429，未校正p = 0.018），但无特征相关性在多重检验下显著。可解释的百分位规则初步测试未能在16项维度比较中稳定超越固定多数基线。研究揭示：低层级符号化总结可暴露特定问题，但无法替代需要上下文感知的音乐判断。
原文摘要 · Abstract (English)
AI-generated covers often fail through local musical errors that a global quality score cannot locate: the vocal contour may remain recognizable while the accompaniment uses the wrong harmonic function, or the output may stay in key while the arrangement remains incomplete. We present a five-dimensional diagnostic framework covering melodic pitch, harmonic progression, key consistency, style consistency, and arrangement/production quality. The benchmark contains 30 covers generated from 5 source songs by 6 systems, with expert severity ratings and 9 symbolic or acoustic features. Harmonic progression and arrangement had the highest severe-error rates (53% and 47%), whereas key consistency was better preserved. Six covers combined acceptable key consistency with severe harmonic errors. Large-leap ratio had a nominal association with melodic ratings (Spearman rho = -0.429, uncorrected p = 0.018), but no feature correlation survived the nine-test multiplicity reference. An interpretable percentile-rule pilot likewise failed to outperform a fixed majority baseline reliably across 16 dimension-level comparisons. The results separate useful diagnostic evidence from dependable automatic scoring: low-level and symbolic summaries can expose particular symptoms, but they do not replace context-aware musical judgment.
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。