Newest papers

NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification

Qingming Li, Ruiyan Sun, Satoshi Nakamura · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28616 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La clasificación de la demencia de descripción de imagen utiliza una escena visual compartida, pero una predicción a nivel de transcripción por sí sola no identifica la evidencia de escena subyacente a sus entradas. NarraSpace vincula palabras y tiempos de habla a elementos de imagen nombrados y recupera pronunciaciones para eventos de escena predefinidos. Los descriptores narrativos-espaciales resumen la cobertura y la organización temporal. Un modelo de lengua congelada contrasta el texto de cada evento bajo ejemplos de la enfermedad de Alzheimer y los participantes en la formación de control de habla saludable, junto con las mediciones de sorpresa de transcripción y cobertura. Los registros de fuente retenidos vinculan los resultados de su evento a sus pronunciaciones de fuente, intervalos de habla y coincidencias léxicas. En el conjunto oficial de pru

Machine translation (Meta M2M100); the English original follows.

Abstract

Picture-description dementia classification uses a shared visual scene, but a transcript-level prediction alone does not identify the scene evidence underlying its inputs. NarraSpace links words and speech times to named picture elements and retrieves utterances for predefined scene events. Narrative-spatial descriptors summarize coverage and temporal organization. A frozen language model contrasts each event's text under examples from Alzheimer's disease and healthy-control training participants, alongside transcript surprisal and coverage measurements. Retained source records link event scores to their source utterances, speech intervals, and lexical matches. On the official 48-participant test set of the Alzheimer's Dementia Recognition through Spontaneous Speech benchmark, a fixed support vector classifier achieves $80.88\%\pm2.56\%$ mean accuracy over fifty seeds; averaged probabilities yield $81.25\%$ accuracy and $91.32\%$ area under the receiver operating characteristic curve. NarraSpace makes the construction of scene-linked classification inputs explicit and inspectable by connecting event-indexed language-model measurements to their source utterances, speech timing, and extraction records. Such source-linked measurements could support clinician review of picture descriptions by presenting quantitative summaries alongside the original speech evidence.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Classifier (UML), Dementia, Natural language processing, Speech recognition, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange