Voice-based digital biomarkers can enable scalable, non-invasive screening and monitoring of Parkinson's disease (PD) and Amyotrophic Lateral Sclerosis (ALS). However, models trained on one cohort or device often fail on new acquisition settings due to cross-device and cross-cohort domain shift. This challenge is amplified in real-world scenarios with partial-label mismatch, where datasets may contain different disease labels and only partially overlap in class space. In addition, voice-based models may exploit demographic cues, raising concerns about gender-related unfairness, particularly when deployed across heterogeneous cohorts. To tackle these challenges, we propose a hybrid framework for unified three-class (healthy/PD/ALS) cross-domain voice classification from partially overlapping cohorts. The method combines style-based domain generalization with conditional adversarial alignment tailored to partial-label settings, reducing negative transfer. An additional adversarial gender branch promotes gender-invariant representations. We conduct a comprehensive evaluation across four heterogeneous sustained-vowel datasets, spanning distinct acquisition settings and devices, under both domain generalization and unsupervised domain adaptation protocols. The proposed approach is compared against twelve state-of-the-art machine learning and deep learning methods, and further evaluated through three targeted ablations, providing the first cross-cohort benchmark and end-to-end domain-adaptive framework for unified healthy/PD/ALS voice classification under partial-label mismatch and fairness constraints. Across all experimental settings, our method consistently achieves the best external generalization over the considered evaluation metrics, while maintaining reduced gender disparities. Notably, no competing method shows statistically significant gains in external performance.

翻译：基于语音的数字生物标志物能够实现帕金森病（PD）和肌萎缩侧索硬化症（ALS）的可扩展、非侵入性筛查与监测。然而，由于跨设备与跨队列的域偏移，在特定队列或设备上训练的模型在新采集环境中常常失效。这一挑战在存在部分标签失配的现实场景中更为突出——数据集中可能包含不同的疾病标签，且类别空间仅部分重叠。此外，基于语音的模型可能利用人口统计学线索，引发对性别相关不公平性的担忧，尤其是在跨异质队列部署时。为应对这些挑战，我们提出一种混合框架，用于从部分重叠队列中实现统一的三分类（健康/PD/ALS）跨域语音分类。该方法结合了基于风格的域泛化技术与针对部分标签场景定制的条件对抗对齐机制，以减少负迁移。额外的对抗性别分支促进了性别不变表征的学习。我们在四个异质持续元音数据集上进行了全面评估，涵盖不同采集环境与设备，并在域泛化和无监督域适应两种协议下进行测试。所提出的方法与十二种先进的机器学习和深度学习方法进行了对比，并通过三项针对性消融实验进一步验证，首次为部分标签失配和公平性约束下的统一健康/PD/ALS语音分类提供了跨队列基准测试和端到端域适应框架。在所有实验设置中，我们的方法在所考虑的评估指标上始终取得最佳的外部泛化性能，同时保持较低的性别差异。值得注意的是，没有任何竞争方法在外部性能上显示出统计学意义的显著提升。