基于迭代对抗自训练的鲁棒跨域语音阿尔茨海默病检测
Robust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training
- Johns Hopkins University（约翰斯·霍普金斯大学）
- University of Michigan（密歇根大学）
- Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对语音AD检测跨域性能退化问题，提出迭代对抗自训练（IAST）无监督域适应方法，学习域不变特征，显著提升跨域泛化与鲁棒性。
AI中文摘要：
随着阿尔茨海默病（AD）日益成为全球重大公共卫生问题，基于语音的AD检测受到广泛关注。然而，现有大多数方法在单一数据集上训练和评估，往往因依赖数据集特定伪影而非疾病相关语音线索，导致严重的跨域性能下降。在实际应用中，可靠的阿尔茨海默病检测要求模型对录音环境、说话人和数据采集条件的变化具有鲁棒性。为应对这一挑战，本文采用无监督域适应，在缺乏目标域诊断标签的情况下学习鲁棒、域不变的特征表示。在此基础上，提出了一种新颖的无监督域适应方法——迭代对抗自训练（IAST）。结果表明，IAST在各种跨域设置下显著提升了泛化能力和鲁棒性。
英文摘要：
As Alzheimer's disease (AD) has increasingly become a major global public health issue, speech-based AD detection has attracted widespread attention. However, most existing methods are trained and evaluated on a single dataset, often leading to severe cross-domain performance degradation due to reliance on dataset-specific artifacts rather than disease-related speech cues. In real-world applications, reliable Alzheimer's disease detection requires models that are robust to variations in recording environments, speakers and data collection conditions. To address this challenge, this paper adopts unsupervised domain adaptation to learn robust, domain-invariant feature representations in the absence of target-domain diagnosis labels. On this basis, a novel unsupervised domain adaptation method, Iterative Adversarial Self-Training (IAST), is proposed. Results demonstrate that IAST significantly improves the generalization ability and robustness under various cross-domain settings.
