Alzheimer's Dementia Detection through Spontaneous Dialogue with Proactive Robotic Listeners

TL;DR

This paper introduces a novel dialogue-based approach using proactive robotic listeners to improve Alzheimer's detection by analyzing spontaneous speech and dialogue patterns, addressing key challenges like disfluencies and limited utterances.

Contribution

It proposes a new AD detection architecture with an ensemble detector and proactive listener module integrated into conversational robots for healthcare.

Findings

Addresses key issues in speech-based AD detection, such as disfluencies and dialogue context.

Integrates dialogue information with speech analysis for improved accuracy.

Proposes a robot-based system for real-time AD screening in healthcare settings.

Abstract

As the aging of society continues to accelerate, Alzheimer's Disease (AD) has received more and more attention from not only medical but also other fields, such as computer science, over the past decade. Since speech is considered one of the effective ways to diagnose cognitive decline, AD detection from speech has emerged as a hot topic. Nevertheless, such approaches fail to tackle several key issues: 1) AD is a complex neurocognitive disorder which means it is inappropriate to conduct AD detection using utterance information alone while ignoring dialogue information; 2) Utterances of AD patients contain many disfluencies that affect speech recognition yet are helpful to diagnosis; 3) AD patients tend to speak less, causing dialogue breakdown as the disease progresses. This fact leads to a small number of utterances, which may cause detection bias. Therefore, in this paper, we propose a novel AD detection architecture consisting of two major modules: an ensemble AD detector and a proactive listener. This architecture can be embedded in the dialogue system of conversational robots for healthcare.