发表机构
The University of Western Australia; The University of New South Wales; Great Bay University（西澳大利亚大学; 新南威尔士大学; 大湾区大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CASM是一种上下文感知的半马尔可夫解码器，用于音乐节拍跟踪，通过利用局部激活证据改善时间连续性并保持事件级F1，优于动态贝叶斯网络基线。
AI 中文摘要
在音乐节拍跟踪中，模型预测的激活必须被解码为离散的、音乐上连贯的事件序列。直接峰值拾取紧密跟随局部证据，但可能保留虚假峰值或错过弱节拍。动态贝叶斯网络（DBNs）作为一种广泛使用的结构化后处理器，在预定义的全局速度、拍号和过渡约束下提高了序列一致性，但其行为可能强烈依赖于这些设置。我们引入了CASM，一种上下文感知的半马尔可夫解码器，它反而将其时间约束条件基于局部激活证据。CASM还考虑了竞争性周期解释之间的模糊性，包括半速和双速替代方案。确定性保障措施防止了不合理输出并保持了节拍-弱拍一致性。应用于来自三个神经节拍跟踪器（BeatThis、MSCNN和TCN）的固定激活时，CASM在GTZAN和SMC数据集上提高了时间连续性，同时保持了事件级F1分数，无需骨干网络重新训练或数据集特定调整。进一步分析表明，CASM对校准数据组成的敏感性低于DBN基线。
英文摘要
In music beat tracking, model-predicted activations must be decoded into a discrete, musically coherent event sequence. Direct peak picking closely follows local evidence but can retain spurious peaks or miss weak beats. Dynamic Bayesian networks (DBNs), a widely used structured post-processor, improve sequence consistency under predefined global tempo, meter, and transition constraints, but their behavior can depend strongly on these settings. We introduce CASM, a context-aware semi-Markov decoder that instead conditions its temporal constraint on local activation evidence. CASM also accounts for ambiguity among competing periodic interpretations, including half- and double-tempo alternatives. Deterministic safeguards prevent implausible outputs and preserve beat-downbeat consistency. Applied to fixed activations from three neural beat trackers (BeatThis, MSCNN, and TCN), CASM improves temporal continuity while preserving event-level F1 across the GTZAN and SMC datasets, without backbone retraining or dataset-specific retuning. Further analysis shows that CASM is less sensitive than the DBN baseline to the composition of the calibration data.
CommentsSubmitted to ICASSP 2027 conference. Code and demo: https://zhanh-he.github.io/casm-beat-tracking
