arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14655cs.CLcs.AI
收藏

突破数据效率困境:一种联邦学习与增强学习框架用于通过语音检测阿尔茨海默病

Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech

Tianjin Key Laboratory of Cognitive Computing and Application(认知计算与应用天津重点实验室);College of Intelligence and Computing, Tianjin University(智能计算学院,天津大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);College of Computer and Data Science, Fuzhou University(计算机与数据科学学院,福州大学);Huiyan Technology (Tianjin) Co., Ltd(慧研科技(天津)有限公司)

Xiao Wei, Bin Wen, Yuqin Lin, Kai Li, Mingyang gu, Xiaobao Wang, Longbiao Wang, Jianwu Dang

AI总结:

FAL-AD通过联邦学习与数据增强框架,实现阿尔茨海默病语音检测中的数据效率提升,达到91.52%的多模态准确率。

摘要:

阿尔茨海默病的早期诊断对于延缓其进展至关重要。尽管基于AI的语音检测是非侵入性和成本效益的,但面临由于医疗数据稀缺和隐私障碍导致的关键数据效率困境。因此,我们提出FAL-AD,一种新颖的框架,通过联邦学习与数据增强的协同整合,系统地优化数据效率。我们的方法实现了三个关键突破:首先,通过基于语音转换的增强方法实现绝对效率提升,该方法通过跨类别的语音内容重组生成多样化的病理语音样本。其次,通过自适应的联邦学习范式实现协同效率突破,在隐私约束下最大化跨机构效益。最后,通过注意力交叉模态融合模型实现表征效率优化,实现精细的词级对齐和语音-文本交互。在ADReSSo上评估,FAL-AD实现了91.52%的多模态准确率,优于所有集中式基线,并展示了一种实际解决方案来解决数据效率困境。我们的源代码可在https://github.com/smileix/fal-ad上公开获取。

英文摘要:

Early diagnosis of Alzheimer's Disease (AD) is crucial for delaying its progression. While AI-based speech detection is non-invasive and cost-effective, it faces a critical data efficiency dilemma due to medical data scarcity and privacy barriers. Therefore, we propose FAL-AD, a novel framework that synergistically integrates federated learning with data augmentation to systematically optimize data efficiency. Our approach delivers three key breakthroughs: First, absolute efficiency improvement through voice conversion-based augmentation, which generates diverse pathological speech samples via cross-category voice-content recombination. Second, collaborative efficiency breakthrough via an adaptive federated learning paradigm, maximizing cross-institutional benefits under privacy constraints. Finally, representational efficiency optimization by an attentive cross-modal fusion model, which achieves fine-grained word-level alignment and acoustic-textual interaction. Evaluated on ADReSSo, FAL-AD achieves a state-of-the-art multi-modal accuracy of 91.52%, outperforming all centralized baselines and demonstrating a practical solution to the data efficiency dilemma. Our source code is publicly available at https://github.com/smileix/fal-ad.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑