轻量级自监督检测基频及单音音乐中发声概率的准确估计
Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music
AI总结：
本文提出了一种轻量级自监督框架，用于单音音乐中基频和发声概率的准确估计，通过转置等价学习和EM风格的迭代加权方案实现无需标注的高效训练。
摘要：
可靠的基频（F0）和发声估计对于神经合成至关重要，但许多音高提取器依赖于大量标注语料库，并在现实录音中的噪声下退化。我们提出了一种轻量级、完全自监督的框架，用于联合F0估计和发声推断，适用于从有限音频中快速单乐器训练。通过在CQT特征上使用转置等价学习，我们引入了一种EM风格的迭代重新加权方案，该方案利用Shift Cross-Entropy（SCE）一致性作为可靠性信号来抑制无信息的噪声/非发声帧。所得权重提供了置信度分数，使伪标签可用于单独的轻量级发声分类器，而无需手动注释。在MedleyDB上训练并在MDB-stem-synth真实数据上评估，我们的方法实现了竞争性的跨语料库性能（RPA 95.84，RCA 96.24）并展示了跨乐器泛化能力。
英文摘要：
Reliable fundamental frequency (F 0) and voicing estimation is essential for neural synthesis, yet many pitch extractors depend on large labeled corpora and degrade under realistic recording artifacts. We propose a lightweight, fully self-supervised framework for joint F 0 estimation and voicing inference, designed for rapid single-instrument training from limited audio. Using transposition-equivariant learning on CQT features, we introduce an EM-style iterative reweighting scheme that uses Shift Cross-Entropy (SCE) consistency as a reliability signal to suppress uninformative noisy/unvoiced frames. The resulting weights provide confidence scores that enable pseudo-labeling for a separate lightweight voicing classifier without manual annotations. Trained on MedleyDB and evaluated on MDB-stem-synth ground truth, our method achieves competitive cross-corpus performance (RPA 95.84, RCA 96.24) and demonstrates cross-instrument generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
