SpiroPhonia：基于自发语音的无创呼吸健康评估
SpiroPhonia: Non-Invasive Respiratory Health Assessment from Spontaneous Speech
浏览论文内容
中文总结 AI 辅助
本文提出SpiroPhonia框架，利用自发语音通过机器学习评估呼吸健康，在201人数据集上达到78%准确率，证明日常语音可编码呼吸生物标志物，支持无创连续监测。
中文摘要 AI 辅助
慢性阻塞性肺疾病（COPD）仍然是全球重大健康挑战，凸显了对可及且无创检测方法的需求。由于语音产生与呼吸生理学密切相关，其异常可作为肺功能受损的间接指标。本研究提出了SpiroPhonia，一种利用自发语音进行呼吸健康评估的机器学习框架。我们在一个包含201名说话者（102名COPD患者，99名健康对照）的新数据集上评估了SpiroPhonia。通过将统计分析（statistical analysis）与递归特征选择（recursive feature selection）相结合，我们识别出一组紧凑的判别性语音标记（discriminative speech markers）。我们的最佳模型达到了78%的准确率、80%的F1分数和87%的AUC。这一在自发语音上的表现与使用受控实验室录音的方法相当。研究结果表明，日常语音编码了稳健的呼吸生物标志物，为通过语音技术实现连续健康监测铺平了道路。
英文摘要
Chronic Obstructive Pulmonary Disease (COPD) remains a major global health challenge, emphasizing the need for accessible and non-invasive detection. Since speech production is fundamentally linked to respiratory physiology, its disruptions can serve as indirect indicators of pulmonary impairment. This study introduces SpiroPhonia, a machine learning framework that leverages spontaneous speech for respiratory health assessment. We evaluated SpiroPhonia on a new dataset of 201 speakers (102 with COPD, 99 healthy controls). By integrating statistical analysis with recursive feature selection, we identified a compact set of discriminative speech markers. Our best model achieved 78% accuracy, 80% F1-score, and 87% AUC. This performance on spontaneous speech is competitive with methods using controlled laboratory recordings. Findings demonstrate that everyday speech encodes robust respiratory biomarkers, paving the way for continuous health monitoring via voice-enabled technologies.
发表机构
- University of Maryland, College Park（马里兰大学学院公园分校）
- DR. M R Khan Shishu Hospital & Institute of Child Health（M R 汗儿童医院与儿童健康研究所）
机构由 AI 辅助整理，请以论文原文为准。
