提出分层特征工程框架，区分声带过度使用类型
A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction
- 构建静态、动态、比率和耦合四类特征，捕捉声源-声道交互
- 对声创伤型分类AUC达0.891，非声创伤型达0.728
- 耦合特征对两类分类均关键，适合语音病理学研究者
可穿戴颈部加速度传感器实现声带过度使用无创监测，但其亚型的可靠生物标志物仍有限。本研究基于NeckVibe Challenge数据集，旨在区分声创伤型（PVH）与非声创伤型（NPVH）及健康对照。提出分层特征工程框架，包含：(i) 静态特征，(ii) 动态特征，(iii) 比率特征，(iv) 耦合特征以捕捉声源-滤波器相互作用。单变量统计分析显示PVH具有强可分性，而NPVH显著性较弱；但经针对高维特征融合设计的机器学习流程处理后，发现耦合特征对两类任务均至关重要。最终实现PVH分类AUC为0.891，NPVH为0.728，表明PVH近似线性可分，而NPVH识别依赖于建模非线性特征交互。
原文摘要 · Abstract (English)
Ambulatory neck-surface acceleration enables non-invasive monitoring of vocal hyperfunction, yet robust biomarkers for its subtypes remain limited. This study investigates the NeckVibe Challenge dataset to distinguish phonotraumatic (PVH) and non-phonotraumatic (NPVH) from healthy controls. We propose a hierarchical feature engineering framework comprising: (i) static, (ii) dynamic, (iii) ratio-based, (iv) coupling features capturing source filter interactions. While univariate statistical analysis shows strong separability for PVH but limited significance for NPVH, our machine learning pipeline, tailored for high-dimensional feature integration, identifies that coupling features are crucial for both tasks. We achieve an AUC of 0.891 for PVH and 0.728 for NPVH, suggesting that while PVH is near-linearly separable, NPVH discrimination benefits from modeling non-linear feature interactions.
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。