Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment

TL;DR

This study investigates the challenges of automatic speech recognition for older adults with cognitive impairments, revealing significant error disparities and identifying acoustic factors influencing ASR accuracy to inform better interface design.

Contribution

The paper provides an empirical analysis of ASR performance across cognitive groups and identifies key acoustic predictors of errors, proposing design strategies for improved voice interfaces for older adults.

Findings

ASR errors are significantly higher for individuals with dementia.

Speech intensity, voice quality, and pause ratio predict ASR accuracy.

Design implications include personalized ASR and adaptive interaction strategies.

Abstract

Millions of people live with cognitive impairment from Alzheimer's disease and related dementias (ADRD). Voice-enabled smart home systems offer promise for supporting daily living but rely on automatic speech recognition (ASR) to transcribe their speech to text. Prior work has shown reduced ASR performance for adults with cognitive impairment; however, the acoustic factors underlying these disparities remain poorly understood. This paper evaluates ASR performance for 83 older adults across cognitive groups (cognitively normal, mild cognitive impairment, dementia) reading commands to a voice assistant (Amazon Alexa). Results show that ASR errors are significantly higher for individuals with dementia, revealing a critical usability gap. To better understand these disparities, we conducted an acoustic analysis of speech features and found that a speaker's intensity, voice quality, and pause ratio predicted ASR accuracy. Based on these findings, we outline HCI design implications for AgeTech and voice interfaces, including speaker-personalized ASR, human-in-the-loop correction of ASR transcripts, and interaction-level personalization to support ability-based adaptation.