改进投票法音高估计，提升准确性和抗噪能力
Voting-based Pitch Estimation with Temporal and Frequential Alignment and Correlation Aware Selection
- 通过时频对齐和相关性筛选，优化多个音高估计器的投票机制
- 在多种语音音乐数据上，干净环境下超越单个顶尖方法
- 适合需要高鲁棒性的音高估计场景，如语音识别、音乐信息检索
投票法是一种用于基频估计的集成方法，虽实证显示其稳健性，但缺乏深入研究。本文提供该方法的有效性理论基础，解释了基频估计误差方差的降低，并引用康多塞陪审团定理说明其在有声/无声检测中的准确性。针对实际局限性，提出两项改进：1）预投票对齐流程，校正估计器间的时序与频率偏差；2）基于误差相关性的贪心算法，选取紧凑而高效的估计器子集。在涵盖语音、歌唱和音乐的多样化数据集上实验表明，采用对齐方法的方案在清洁条件下优于单个最先进的估计器，在噪声环境中仍保持稳健的有声/无声检测能力。
原文摘要 · Abstract (English)
The voting method, an ensemble approach for fundamental frequency estimation, is empirically known for its robustness but lacks thorough investigation. This paper provides a principled analysis and improvement of this technique. First, we offer a theoretical basis for its effectiveness, explaining the error variance reduction for fundamental frequency estimation and invoking Condorcet's jury theorem for voiced/unvoiced detection accuracy. To address its practical limitations, we propose two key improvements: 1) a pre-voting alignment procedure to correct temporal and frequential biases among estimators, and 2) a greedy algorithm to select a compact yet effective subset of estimators based on error correlation. Experiments on a diverse dataset of speech, singing, and music show that our proposed method with alignment outperforms individual state-of-the-art estimators in clean conditions and maintains robust voiced/unvoiced detection in noisy environments.
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。