跳到正文
arXiv cs.CY· Hiba Akhaddar, Peter Plantinga, Mirco Ravanelli, Tristan Glatard·· 23 小时前AI 评分31

研究发现帕金森病语音检测存在性别差异,单一性别训练的模型难以泛化

Sex Differences in the Detection of Parkinson's Disease from Speech

AI 导读

一项基于深度学习与传统机器学习的研究发现,帕金森病语音检测存在明显性别差异:在较大数据集上女性说话者的分类准确率高于男性,且仅用单一性别数据训练的模型无法泛化到另一性别。研究使用三个预训练语音模型的嵌入向量,结合手工声学特征与多种分类器,在四个持续发声数据集的性别平衡子集上开展实验,并尽可能控制年龄变量。作者据此强调,开发帕金森病检测系统时应将性别作为变量纳入考量。

正文 · 原文

View PDF HTML (experimental)

Abstract:Parkinson's disease (PD) is the second most common neurodegenerative disease in the world, and 70\% to 75\% of PD patients suffer from speech disorders at some stage. Since PD affects men more frequently than women, previous publications tend to rely on unbalanced datasets that potentially introduce sex biases into trained models. This study investigates sex differences in PD detection from speech using deep learning and traditional machine learning approaches. We evaluated speech-based PD detection using embeddings from three pre-trained speech models, combined with handcrafted acoustic features and different classifiers. Sex-specific experiments were conducted on balanced subsets of four sustained phonation datasets, controlling for sex, disease status, and, where possible, age. All recordings were obtained during a sustained phonation task. Results show that female speakers were more accurately classified than male speakers in the larger dataset. Sex-specific results show that when the models are trained on one sex, they fail to generalize to the other one. Our results highlight the importance of including sex as a variable in the development of PD detection systems.
Comments: 12 pages, 3 figures
Subjects: Audio and Speech Processing (eess.AS); Computers and Society (cs.CY); Machine Learning (cs.LG)
Cite as: arXiv:2611.24741 [eess.AS]
  (or arXiv:2611.24741v1 [eess.AS] for this version)
  https://doi.org/10.48550/arXiv.2611.24741

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hiba Akhaddar [view email]
[v1] Wed, 18 Nov 2026 16:57:24 UTC (226 KB)

来源:arXiv cs.CY · arxiv.org