用联邦学习+语音增强，解决阿尔茨海默病诊断数据少且难共享的难题
Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech
- 通过跨类别语音内容重组生成病理语音样本，提升数据多样性
- 在隐私保护下实现多机构协作，模型准确率达91.52%创纪录
- 适合医疗AI研究者和需要隐私安全训练的团队使用
阿尔茨海默病早期诊断对延缓病情进展至关重要。尽管基于人工智能的语音检测具有无创、低成本优势，但受限于医疗数据稀缺与隐私保护壁垒，面临严重数据效率困境。为此，我们提出FAL-AD框架，融合联邦学习与数据增强，系统性优化数据效率。该方法实现三大突破：首先，基于语音转换的数据增强生成多样病理语音样本；其次，采用自适应联邦学习范式，在隐私约束下实现跨机构协同优化；最后，通过注意力驱动的跨模态融合模型，实现词级对齐与声学-文本交互。在ADReSSo数据集上，FAL-AD达到91.52%的多模态分类准确率，超越所有集中式基线，为数据效率难题提供实用解决方案。源代码已公开于https://github.com/smileix/fal-ad。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。