用最优传输方法提升音高估计的自监督学习效果

Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport

• 基于最优传输构建平移等变的自监督学习框架
• 在单音高估计任务中实现更稳定高效的训练
• 适合对音高估计与自监督学习感兴趣的研究者

本文提出一种基于最优传输的优化目标，用于训练一维平移等变系统，并验证其在单音高估计任务中的适用性。该方法为当前先进的自监督音高估计算法提供了理论基础更扎实、数值更稳定且实现更简单的训练替代方案。

原文摘要 · Abstract (English)

In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation. Our method provides a theoretically grounded, more numerically stable, and simpler alternative for training state-of-the-art self-supervised pitch estimators.

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。