通过删减4/4节拍间隔，提升非4/4节拍的识别能力。
Skip That Beat: Augmenting Meter Tracking Models for Underrepresented Time Signatures
- 从4/4数据中移除节拍间隔，增强2/4和3/4节拍的表示。
- 在两种模型上均提升非主流节拍的强拍追踪性能。
- 对未见过的巴西桑巴音乐数据也有改进效果。
现有强拍与节拍追踪模型主要基于4/4拍音乐数据训练，导致对其他节拍（如2/4拍的巴西桑巴）泛化能力差。本文提出一种简单数据增强方法：从4/4标注音频中移除部分节拍间隔，以增加2/4和3/4节拍的代表性。实验表明，该方法可有效提升非主流节拍的强拍追踪性能，同时保持4/4拍整体节拍追踪表现不变。此外，在未见过的桑巴音乐数据集上也观察到强拍追踪性能提升。
原文摘要 · Abstract (English)
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.
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。