用分段序列建模提升复杂和罕见和弦识别效果
An event-based sequence modeling approach to recognizing non-triad chords with oversegmentation minimization
- 将和弦识别改为按片段的序列生成，避免逐帧预测
- 对复杂和弦识别准确率提升显著，尤其低频类型
- 适合音乐分析、自动配乐等需要精准和弦分割的场景
自动和弦识别（ACR）从音乐音频中提取时间对齐的和弦标签。尽管近年有进展，但依然面临过度分割、数据稀缺和类别不平衡问题，尤其在识别非三度和弦（non-triads）时表现不佳，因现有数据集缺乏此类样本。本文将ACR重新建模为分段级的序列到序列预测任务，采用自回归方式生成和弦序列，而非逐帧预测，仅在片段边界检测和弦变化，从而减少过度分割。此外，设计了两种特定于时间对齐和弦建模的词元表示方法，并提出一种编码器预训练策略。实验表明，该模型在和弦识别与分割性能上均有提升，对复杂和稀有和弦类型效果尤为明显。结果证明分段级序列建模、结构化词元化及表示学习能有效推动和弦识别系统发展。
原文摘要 · Abstract (English)
Automatic chord recognition (ACR) extracts time-aligned chord labels from music audio recordings. Despite recent advances, ACR still struggles with oversegmentation, data scarcity, and imbalance, especially in recognizing complex chords such as non-triads, which are unpopular in existing datasets. To address these challenges, we reformulate ACR as a segment-level sequence-to-sequence prediction task, where chord sequences are predicted auto-regressively rather than frame by frame. This design mitigates excessive segmentation by detecting chord changes only at segment boundaries. We further introduce two types of token representations and an encoder pre-training method, both specifically designed for time-aligned chord modeling. Experimental results show that our model improves performance in both chord recognition and segmentation, with notable gains for complex and infrequent chord types. These findings demonstrate the effectiveness of segment-level sequence modeling, structured tokenization, and representation learning for advancing chord recognition systems.
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。