Metraipolis › archive › dc_cb144d4c2e90
LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection — arXiv:2609.10896
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10896
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:40:40.372Z
- SHA-256 of the archived text
dc01a858556a5656ba70ab85513b90f4c2268ef44f0259ba5fd28345f2cabe1a- Stable URL of this page
https://metraipolis.com/documento/dc_cb144d4c2e90
How to cite
LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection — arXiv:2609.10896 — arXiv (en), https://arxiv.org/abs/2609.10896 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb144d4c2e90 (Metraipolis archive dc_cb144d4c2e90, sha256 dc01a858556a5656ba70ab85513b90f4c2268ef44f0259ba5fd28345f2cabe1a)
BibTeX
@misc{dccb144d4c2e90,
title = {LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection — arXiv:2609.10896},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10896},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb144d4c2e90; sha256 dc01a858556a5656ba70ab85513b90f4c2268ef44f0259ba5fd28345f2cabe1a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10896. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speech-based automatic detection of Alzheimer's disease (AD) provides a non-invasive and scalable approach to early cognitive screening. AD affects both lexical-semantic organization and speech production, including atypical pauses and word elongations. However, existing methods have yet to fully integrate these paralinguistic cues with linguistic content. We propose LLM-Anchored Paralinguistic Enrichment (LAPE), which enriches LLM-derived linguistic representations with paralinguistic cues through three coordinated innovations. The first is prosodic event textualization, which enables the LLM to model pauses and elongations jointly with lexical content by encoding them as explicit markers with bounded duration-aware repetition. The second is lexico-prosodic unitization and chunking, which preserves event identity and magnitude in both modalities by pooling only consecutive word units. The third is text-anchored paralinguistic fusion, which integrates local and utterance-level speech features by using NormGate to normalize and dynamically scale them relative to text. We evaluate LAPE on ADReSS and ADReSSo using participant-level cross-validation and leave-one-subject-out evaluation. LAPE achieves state-of-the-art performance across all four primary settings. Code will be released upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2609.10896 — 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 2026-10-16T05:23:56.982Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).