跳过那一拍：为代表性不足的拍号增强节拍跟踪模型
Skip That Beat: Augmenting Meter Tracking Models for Underrepresented Time Signatures
AI总结：
提出一种通过移除4/4拍曲目中的节拍间隔来增强数据的方法，以提升2/4和3/4拍等代表性不足拍号的强拍跟踪性能，同时保持节拍跟踪整体性能。
摘要：
节拍和强拍跟踪模型主要使用4/4拍音乐的数据集进行开发，这降低了它们对其他拍号曲目（如2/4拍的巴西桑巴）的泛化能力。在这项工作中，我们提出了一种简单的增强技术，以增加4/4拍以外拍号（即2/4和3/4拍）的表示。我们的增强过程通过从4/4拍标注曲目中移除节拍间隔来实现。我们表明，增强数据有助于改善代表性不足的拍号的强拍跟踪，同时保持两种不同模型中节拍跟踪的整体性能。我们还表明，该技术有助于在未见过的桑巴数据集中改善强拍跟踪。
英文摘要：
Beat and downbeat tracking models are predominantly developed using datasets with music in 4/4 meter, which decreases their generalization to repertories in other time signatures, such as Brazilian samba which is in 2/4. In this work, we propose a simple augmentation technique to increase the representation of time signatures beyond 4/4, namely 2/4 and 3/4. Our augmentation procedure works by removing beat intervals from 4/4 annotated tracks. We show that the augmented data helps to improve downbeat tracking for underrepresented meters while preserving the overall performance of beat tracking in two different models. We also show that this technique helps improve downbeat tracking in an unseen samba dataset.
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。
