改进音乐转录中的音符起始点对齐，提升弱对齐数据的可用性。
Snapping Matters: Context-Aware Onset Refinement for Automatic Music Transcription
- 将音符对齐建模为跨音高的二分图匹配问题，实现上下文感知决策
- 在钢琴、室内乐和管弦乐数据上，相比贪心方法提升对齐精度与转录准确率
- 尤其适合处理初始对齐粗糙或对齐窗口较宽的弱监督训练数据
精确的音符级标注对训练自动音乐转录系统至关重要，尤其是音符起始点标签，构成近年多数AMT系统的核心。然而，真实录音的高质量标注数据稀缺。序列级评分-音频对齐方法（如动态时间规整）仅提供粗略对应，需局部精修步骤——即“对齐”（snapping），通过神经网络生成的起始置信度图峰值调整对齐后的评分起始点，常决定弱对齐的评分-音频对是否可作为有效训练数据。尽管重要，对齐通常被视为简单后处理启发式，采用局部贪心策略。本文系统分析了无乐器特异性转录器的对齐策略，证明其对从弱对齐数据中学习至关重要。基于此，我们将对齐形式化为每音高分配问题，通过二分图匹配求解，在重叠精修窗口和不确定初始对齐下实现上下文感知的起始点决策。跨钢琴、室内乐与管弦乐数据集的大量实验表明，该方法优于贪心对齐，且对齐窗口越宽、初始对齐越粗糙时增益越大。定性示例见项目页面：https://abhirupsaha8.github.io
原文摘要 · Abstract (English)
Precise note-level annotations are critical for training automatic music transcription (AMT) systems, in particular note-onset labels, which form a core component of many recent AMT systems. However, high-quality annotations for real-world recordings are scarce. Sequence-level score--audio alignment methods such as dynamic time warping provide only coarse correspondence, making a local refinement step necessary. This refinement step, known as snapping, adjusts aligned score onsets using peaks in a neural onset posteriorgram and often determines whether weakly aligned score--audio pairs become usable training data at all. Despite its practical importance, snapping is typically treated as a simple post-processing heuristic and implemented with greedy local decisions. We present a systematic analysis of snapping strategies for training instrument-agnostic transcribers, demonstrating that snapping is essential for learning from weakly aligned data. Building on this, we formulate snapping as a per-pitch assignment problem and solve it via bipartite graph matching, yielding context-aware onset decisions under overlapping refinement windows and uncertain initial alignments. Extensive cross-dataset experiments across piano, chamber, and orchestral recordings show improved onset alignment and transcription accuracy over greedy snapping, with gains increasing for wider snapping windows and coarser initial alignments. Qualitative examples are provided on our project page: https://abhirupsaha8.github.io
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。