Metraipolis › archive › dc_67668c15cc09

Why Alzheimer's Speech Screening Fails to Generalize: Bridging the Deployment Gap via Cross-Corpus Evidence Anchoring — arXiv:2609.31293

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31293
License (as archived)
CC0-1.0
Archived
2026-10-08T02:04:16.996Z
SHA-256 of the archived text
dcd810a64be7721e198bb4008c0e8a6a1beae8fb2c192ff6d4c65c3798563674
Stable URL of this page
https://metraipolis.com/documento/dc_67668c15cc09

How to cite

Why Alzheimer's Speech Screening Fails to Generalize: Bridging the Deployment Gap via Cross-Corpus Evidence Anchoring — arXiv:2609.31293 — arXiv (en), https://arxiv.org/abs/2609.31293 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67668c15cc09 (Metraipolis archive dc_67668c15cc09, sha256 dcd810a64be7721e198bb4008c0e8a6a1beae8fb2c192ff6d4c65c3798563674)
BibTeX
@misc{dc67668c15cc09,
  title = {Why Alzheimer's Speech Screening Fails to Generalize: Bridging the Deployment Gap via Cross-Corpus Evidence Anchoring — arXiv:2609.31293},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31293},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67668c15cc09; sha256 dcd810a64be7721e198bb4008c0e8a6a1beae8fb2c192ff6d4c65c3798563674},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31293. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech-based screening is a promising, non-invasive approach for detecting Alzheimer's disease and related cognitive risks. However, models trained on a single domain often generalize poorly to unseen languages, tasks, or recording protocols. This paper investigates this deployment gap using a leave-one-corpus-out evaluation across four distinct datasets. Among 70 interpretable speech and language features, 59 exhibit direction conflicts between healthy control and cognitive risk groups across corpora, with pause, silence, and speech rate showing high protocol sensitivity. Furthermore, while the XLM-R text baseline achieves strong average performance, its Area Under the ROC Curve (AUC) drops to 0.520 on the weakest held-out domain. A standard GroupDRO baseline reaches a 0.766 mean speaker AUC and a 0.504 worst-domain AUC under the same protocol. To address this, we propose a fusion method that integrates XLM-R text baseline scores with evidence anchors selected during training. Balanced fusion achieves a 0.785 mean speaker AUC, while anchor-heavy fusion raises the worst-case speaker AUC to 0.615. This work highlights the need to audit feature transferability and report worst-case domain robustness in cognitive speech screening.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CL).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.31293 — 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 2026-10-08T01:38:49.489Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).