Metraipolis › archive › dc_01461edf51bf

Robust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training — arXiv:2609.14139

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14139
License (as archived)
CC0-1.0
Archived
2026-10-16T02:58:51.389Z
SHA-256 of the archived text
1281770b7f5d969d880ab919552a55774a97fc118613b499736ff1a17b6aca83
Stable URL of this page
https://metraipolis.com/documento/dc_01461edf51bf

How to cite

Robust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training — arXiv:2609.14139 — arXiv (en), https://arxiv.org/abs/2609.14139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01461edf51bf (Metraipolis archive dc_01461edf51bf, sha256 1281770b7f5d969d880ab919552a55774a97fc118613b499736ff1a17b6aca83)
BibTeX
@misc{dc01461edf51bf,
  title = {Robust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training — arXiv:2609.14139},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14139},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01461edf51bf; sha256 1281770b7f5d969d880ab919552a55774a97fc118613b499736ff1a17b6aca83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in eess.AS).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.14139 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:45:36.505Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).