用音频模型评估钢琴演奏，比传统符号方法更准
Audio Foundation Models Outperform Symbolic Representations for Piano Performance Evaluation
- 用预训练音频模型直接分析演奏音色与表现力
- 在19个感知维度上，音频模型效果提升55%
- 适合音乐人工智能、自动评分系统研究者
自动钢琴演奏评价传统依赖符号（MIDI）表示，仅捕捉音符信息，忽略体现表现力的声学细节。本文提出使用预训练音频基础模型（MuQ和MERT）预测19个感知维度的演奏质量。基于PercePiano MIDI文件合成的音频（使用Pianoteq音源），在相同数据源下对比音频与符号方法。最佳模型（MuQ层9-12，配合Pianoteq音源增强）达到R² = 0.537（95%置信区间：[0.465, 0.575]），相比符号基线（R² = 0.347）提升55%，统计显著（p < 10⁻²⁵），且在全部19个维度上均更优。通过跨音源泛化验证（R² = 0.534 ± 0.075）、外部数据集难度相关性分析（rho = 0.623）及多演奏者一致性检验，证实方法有效性。音频-符号融合分析显示误差高度相关（r = 0.738），说明融合无实质增益：音频表示已足够。论文发布完整训练流程、预训练模型与推理代码。
原文摘要 · Abstract (English)
Automated piano performance evaluation traditionally relies on symbolic (MIDI) representations, which capture note-level information but miss the acoustic nuances that characterize expressive playing. I propose using pre-trained audio foundation models, specifically MuQ and MERT, to predict 19 perceptual dimensions of piano performance quality. Using synthesized audio from PercePiano MIDI files (rendered via Pianoteq), I compare audio and symbolic approaches under controlled conditions where both derive from identical source data. The best model, MuQ layers 9-12 with Pianoteq soundfont augmentation, achieves R^2 = 0.537 (95% CI: [0.465, 0.575]), representing a 55% improvement over the symbolic baseline (R^2 = 0.347). Statistical analysis confirms significance (p < 10^-25) with audio outperforming symbolic on all 19 dimensions. I validate the approach through cross-soundfont generalization (R^2 = 0.534 +/- 0.075), difficulty correlation with an external dataset (rho = 0.623), and multi-performer consistency analysis. Analysis of audio-symbolic fusion reveals high error correlation (r = 0.738), explaining why fusion provides minimal benefit: audio representations alone are sufficient. I release the complete training pipeline, pretrained models, and inference code.
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。