Metraipolis › archive › dc_8f2c87903671
Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment? — arXiv:2610.01846
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01846
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:57:34.317Z
- SHA-256 of the archived text
366be018da3228310da86de40e51722d97387b4eb934619f3c961a4fed42fe32- Stable URL of this page
https://metraipolis.com/documento/dc_8f2c87903671
How to cite
Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment? — arXiv:2610.01846 — arXiv (en), https://arxiv.org/abs/2610.01846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f2c87903671 (Metraipolis archive dc_8f2c87903671, sha256 366be018da3228310da86de40e51722d97387b4eb934619f3c961a4fed42fe32)
BibTeX
@misc{dc8f2c87903671,
title = {Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment? — arXiv:2610.01846},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01846},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f2c87903671; sha256 366be018da3228310da86de40e51722d97387b4eb934619f3c961a4fed42fe32},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors. We ask whether such factors are merely encoded in SSL representations or can systematically alter predictions. Using ADReSSo and three large SSL backbones, we apply controlled noise and reverberation interventions to participant-speech-only, non-speech, and full-recording audio. We combine layer-wise linear decoding, input- and representation-space interventions, and geometric alignment analysis to distinguish acoustic decodability from influence on AD prediction. Our results show that controlled acoustic interventions alter AD predictions across all three SSL backbones. Noise, despite showing no significant diagnostic-group difference in the original data, produces the strongest intervention effects. Importantly, these effects are systematically structured relative to the classifier's decision direction, replicate on the held-out test set and reverse when the representation-space intervention direction is reversed. Together, these findings show that high predictive performance and the absence of a significant diagnostic-group difference in a measured acoustic factor are not sufficient for robustness. We argue that intervention-based robustness tests should become standard for trustworthy clinical speech models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.01846 — 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 2026-10-06T12:15:34.847Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).