把拍子检测当成时序目标检测，用简单方法提升精度
Beat Tracking as Object Detection
- 将拍子检测转为一维时序目标检测，用框表示拍子区间
- 在标准数据集上达到与主流模型相当的准确率
- 无需复杂后处理，非极大值抑制简化了传统追踪流程
近期的拍子与强拍检测模型（如RNN、TCN、Transformer）输出帧级激活。本文提出将该任务重新建模为对象检测，将拍子与强拍视为时间上的“对象”。借鉴计算机视觉中的FCOS检测器，将其主干网络替换为WaveBeat的时序特征提取器，并加入特征金字塔网络以捕捉多尺度时序模式。模型预测重叠的拍子/强拍区间及其置信度，随后通过非极大值抑制（NMS）选出最终结果。该NMS步骤作用类似传统追踪器中的动态贝叶斯网络（DBNs），但更简洁且少依赖启发式规则。在标准音乐数据集上的评估显示，本方法仅需少量适配即可实现有竞争力的性能，证明对象检测技术能有效建模音乐拍子。
原文摘要 · Abstract (English)
Recent beat and downbeat tracking models (e.g., RNNs, TCNs, Transformers) output frame-level activations. We propose reframing this task as object detection, where beats and downbeats are modeled as temporal "objects." Adapting the FCOS detector from computer vision to 1D audio, we replace its original backbone with WaveBeat's temporal feature extractor and add a Feature Pyramid Network to capture multi-scale temporal patterns. The model predicts overlapping beat/downbeat intervals with confidence scores, followed by non-maximum suppression (NMS) to select final predictions. This NMS step serves a similar role to DBNs in traditional trackers, but is simpler and less heuristic. Evaluated on standard music datasets, our approach achieves competitive results, showing that object detection techniques can effectively model musical beats with minimal adaptation.
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。