Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.14655 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908836135174144 |
|---|---|
| author | Wei, Xiao Wen, Bin Lin, Yuqin Li, Kai gu, Mingyang Wang, Xiaobao Wang, Longbiao Dang, Jianwu |
| author_facet | Wei, Xiao Wen, Bin Lin, Yuqin Li, Kai gu, Mingyang Wang, Xiaobao Wang, Longbiao Dang, Jianwu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14655 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech Wei, Xiao Wen, Bin Lin, Yuqin Li, Kai gu, Mingyang Wang, Xiaobao Wang, Longbiao Dang, Jianwu Computation and Language Artificial Intelligence 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. |
| title | Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.14655 |