用少量标注数据提升非洲巴西马拉卡图音乐节拍检测精度
Towards Human-in-the-Loop Onset Detection: A Transfer Learning Approach for Maracatu
- 用迁移学习微调时序卷积网络，仅需每乐器5秒标注片段
- 节拍检测任务内迁移效果最佳，F1最高达0.998，提升超50个百分点
- 适合小样本、非西方音乐传统研究者，降低人工标注成本
我们探索了在非洲巴西马拉卡图传统音乐中应用迁移学习进行音乐节拍检测的方法。该传统具有复杂的节奏模式，对常规模型构成挑战。我们采用两种时序卷积网络架构：一种为节拍检测任务预训练（任务内迁移），另一种为节拍跟踪任务预训练（任务间迁移）。通过每乐器仅5秒的标注片段，利用逐层重训练策略对五种传统打击乐器进行微调。结果表明，相较于基线模型，性能显著提升，在任务内设置下F1得分最高达0.998，最佳情况下提升超过50个百分点。跨任务迁移对时间保持类乐器尤为有效，因其节拍位置天然与强拍对齐。最优微调配置因乐器而异，凸显乐器特异性适应策略的重要性。该方法解决了代表性不足音乐传统的难题，提供了一种高效的人机协同方案，极大减少标注工作量同时最大化性能。研究成果有助于构建更包容的音乐信息检索工具，适用于非西方音乐语境。
原文摘要 · Abstract (English)
We explore transfer learning strategies for musical onset detection in the Afro-Brazilian Maracatu tradition, which features complex rhythmic patterns that challenge conventional models. We adapt two Temporal Convolutional Network architectures: one pre-trained for onset detection (intra-task) and another for beat tracking (inter-task). Using only 5-second annotated snippets per instrument, we fine-tune these models through layer-wise retraining strategies for five traditional percussion instruments. Our results demonstrate significant improvements over baseline performance, with F1 scores reaching up to 0.998 in the intra-task setting and improvements of over 50 percentage points in best-case scenarios. The cross-task adaptation proves particularly effective for time-keeping instruments, where onsets naturally align with beat positions. The optimal fine-tuning configuration varies by instrument, highlighting the importance of instrument-specific adaptation strategies. This approach addresses the challenges of underrepresented musical traditions, offering an efficient human-in-the-loop methodology that minimizes annotation effort while maximizing performance. Our findings contribute to more inclusive music information retrieval tools applicable beyond Western musical contexts.
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。