Understanding Dementia Speech Alignment with Diffusion-Based Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mansi, Lepipas, Anastasios, Woszczyk, Dominika, Guan, Yiying, Demetriou, Soteris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908487624163328
author Mansi
Lepipas, Anastasios
Woszczyk, Dominika
Guan, Yiying
Demetriou, Soteris
author_facet Mansi
Lepipas, Anastasios
Woszczyk, Dominika
Guan, Yiying
Demetriou, Soteris
contents Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected that such models can align input text and generated image in the same latent space little has been done to understand whether this alignment is possible between pathological speech and generated images. In this work, we examine the ability of such models to align dementia-related speech information with the generated images and develop methods to explain this alignment. Surprisingly, we found that dementia detection is possible from generated images alone achieving 75% accuracy on the ADReSS dataset. We then leverage explainability methods to show which parts of the language contribute to the detection.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09385
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
Mansi
Lepipas, Anastasios
Woszczyk, Dominika
Guan, Yiying
Demetriou, Soteris
Machine Learning
Artificial Intelligence
Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected that such models can align input text and generated image in the same latent space little has been done to understand whether this alignment is possible between pathological speech and generated images. In this work, we examine the ability of such models to align dementia-related speech information with the generated images and develop methods to explain this alignment. Surprisingly, we found that dementia detection is possible from generated images alone achieving 75% accuracy on the ADReSS dataset. We then leverage explainability methods to show which parts of the language contribute to the detection.
title Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.09385