掩码扩散实现连贯节拍跟踪
Masked diffusion enables coherent beat tracking
AI总结：
该研究针对节拍跟踪神经网络的无效输出问题，提出经三项改进的掩码扩散方法，减少不稳定行为并提升了节拍跟踪性能。
AI中文摘要：
当前用于节拍跟踪的神经网络会生成无效输出，例如连续重拍和不稳定的速度变化，即便训练数据中不存在此类情况。繁重的后处理技术可缓解这些问题，但这种不一致行为的根本原因仍未知。我们假设其源于对多个合理输出节拍网格的建模不足，导致竞争解释的无效混合。我们提出一种掩码扩散（masked diffusion）方法，该方法能正确建模多个输出，并使模型通过迭代推理构建连贯预测。我们对标准掩码扩散进行三项改进以使其适用于节拍跟踪：训练和推理期间对节拍与重拍进行独立掩码、推理时的平衡掩码调度器，以及推理步骤间的峰值拾取。我们的方法减少了不稳定行为并提升了节拍跟踪性能。
英文摘要：
Current neural networks for beat tracking generate invalid outputs, such as consecutive downbeats and erratic tempo changes, even when these are not present in the training data. Heavy post-processing techniques can alleviate these problems, but the original cause of this inconsistent behaviour remains unknown. We hypothesise that it stems from inadequate modelling of multiple plausible output beat grids, resulting in an invalid mixture of competing interpretations. We propose a masked diffusion approach that properly models multiple outputs and enables the model to build coherent predictions through iterative inference. We devise three modifications to standard masked diffusion that enable its application to beat tracking: independent masking of beats and downbeats during training and inference, a balanced masking scheduler for inference, and peak-picking across inference steps. Our approach reduces erratic behaviours and improves beat-tracking performance.
