信号感知的时间路由用于黑胶缺陷状态检测
Signal-Informed Temporal Routing for Vinyl Defect Regime Detection
- Columbia University（哥伦比亚大学）
- Recognition Technologies, Inc.（识别技术公司）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出一种轻量级两阶段黑胶缺陷检测器，利用信号感知专家与时间后端分层解码，在合成基准上宏F1达0.730，较帧级路由提升0.043。
中文摘要 AI 辅助
黑胶修复系统在选择修复操作之前，必须区分孤立的咔嗒声、短促的爆裂声、密集的噼啪声以及重叠的损伤。我们提出了一种轻量级的两阶段检测器，其中信号感知的稀疏、爆裂和密集专家产生互补的缺陷证据，时间后端将该证据转换为稳定的修复状态。该后端将五路决策分层分解，应用仅验证的混合状态门控，并使用验证选择的转移惩罚进行解码，在相同发射上优于最大似然转移矩阵。在从21个录音中提取的597个不重叠的15秒片段的源分离合成基准上，保留系统达到0.730的合并五类宏F1分数（95%置信区间0.694-0.761），比平坦的帧级路由器提高了0.043（配对自举p=0.001）。干净和密集帧高度可靠，而稀疏、爆裂和混合帧则更加模糊。
英文摘要
Vinyl restoration systems must distinguish isolated clicks, short bursts, dense crackle, and overlapping damage before selecting a repair operation. We present a lightweight two-stage detector in which signal-informed sparse, burst, and dense experts produce complementary defect evidence, and a temporal backend converts that evidence into stable repair regimes. The backend factors the five-way decision hierarchically, applies a validation-only mixed regime gate, and decodes with validation-selected transition penalties that outperform a maximum-likelihood transition matrix on the same emissions. On a source-separated synthetic benchmark of 597 non-overlapping 15 s excerpts drawn from 21 recordings, the held-out system reaches 0.730 pooled five-class macro F1 (95% CI 0.694-0.761), an improvement of 0.043 over a flat frame-level router (paired bootstrap p=0.001). Clean and dense frames are highly reliable, while sparse, burst, and mixed frames remain far more ambiguous.
