{"slug": "llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection", "title": "LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection", "summary": "Researchers introduced LLM-Anchored Paralinguistic Enrichment (LAPE), a method that combines LLM-derived linguistic representations with paralinguistic speech cues to detect Alzheimer's disease, achieving state-of-the-art performance across all four primary settings on the ADReSS and ADReSSo datasets. LAPE uses three coordinated innovations: prosodic event textualization, which encodes pauses and word elongations as explicit duration-aware markers; lexico-prosodic unitization and chunking, which pools only consecutive word units; and text-anchored paralinguistic fusion, which uses NormGate to normalize and dynamically scale local and utterance-level speech features relative to text. The work was evaluated with participant-level cross-validation and leave-one-subject-out evaluation, and the code will be released upon acceptance.", "body_md": "arXiv:2609.10896v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection", "canonical_source": "https://arxiv.org/abs/2609.10896", "published_at": "2026-09-11 04:00:00+00:00", "updated_at": "2026-09-11 04:26:06.958199+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research"], "entities": ["LLM-Anchored Paralinguistic Enrichment", "LAPE", "ADReSS", "ADReSSo", "NormGate", "Alzheimer's disease"], "alternates": {"html": "https://wpnews.pro/news/llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection", "markdown": "https://wpnews.pro/news/llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection.md", "text": "https://wpnews.pro/news/llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection.txt", "jsonld": "https://wpnews.pro/news/llm-anchored-paralinguistic-enrichment-for-alzheimer-s-disease-detection.jsonld"}}