Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment
The DOI matches its Crossref record; 95 of the 95 references it cites were found in a registry or an index.
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Fitting Linear Mixed-Effects Models Using lme4
Bates, D., Mächler, M., Bolker, B., & Walker, S. (2015) · Journal of Statistical Software · doi:10.18637/jss.v067.i01 · Cited by 86,835 · cited 1×
“An alternative explanation is that the task analyzed in the present study – reading pre-scripted commands – might have obscured differences that could emerge between cognitively normal and adults with MCI in spontaneous speech (e.g., [56, 82]).”
The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment
Nasreddine, Z. S., Phillips, N. A., Bédirian, V., Charbonneau, S., Whitehead, V., Collin, I., Cummings, J. L., & Chertkow, H. (2005) · Journal of the American Geriatrics Society · doi:10.1111/j.1532-5415.2005.53221.x · Cited by 25,553 · cited 1×
“Next, we matched the ‘ground truth’ human annotated transcript with the intended command (see Appendix A).”
Random effects structure for confirmatory hypothesis testing: Keep it maximal
Barr, D. J., Levy, R., Scheepers, C., & Tily, H. J. (2013) · Journal of Memory and Language · doi:10.1016/j.jml.2012.11.001 · Cited by 10,328 · cited 1×
“In the cases of singularity or convergence errors, the random effects structure was simplified [9].”
performance: An R Package for Assessment, Comparison and Testing of Statistical Models
Lüdecke, D., Ben-Shachar, M., Patil, I., Waggoner, P., & Makowski, D. (2021) · Journal of Open Source Software · doi:10.21105/joss.03139 · Cited by 5,836 · cited 1×
“We assessed collinearity with the performance R package [53].”
2024 Alzheimer's disease facts and figures
(2024) · Alzheimer's & Dementia · doi:10.1002/alz.13809 · Cited by 2,536
Robust Speech Recognition via Large-Scale Weak Supervision
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022) · arXiv · doi:10.48550/arxiv.2212.04356 · Cited by 1,953
Luger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176 · cited 2×
“Understanding these errors has important implications for Human-Computer Interaction (HCI) frameworks.”
Racial disparities in automated speech recognition
Koenecke, A., Nam, A., Lake, E., Nudell, J., Quartey, M., Mengesha, Z., Toups, C., Rickford, J. R., Jurafsky, D., & Goel, S. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1915768117 · Cited by 765 · cited 4×
“This text transcript is then passed to a natural language understanding (NLU) model and/or large language model (LLM) to interpret the user’s utterance and generate an appropriate response.”
InfluentialA Survey on Ambient Intelligence in Healthcare
Acampora, G., Cook, D. J., Rashidi, P., & Vasilakos, A. V. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2262913 · Cited by 630 · cited 1×
“For example, studies have investigated smart homes utilizing sensor-based monitoring systems that detect human activities, identify anomalies in daily routines, and even provide reminders or alerts to external caregivers [1, 52, 77].”
Praat script to detect syllable nuclei and measure speech rate automatically
de Jong, N. H., & Wempe, T. (2009) · Behavior Research Methods · doi:10.3758/brm.41.2.385 · Cited by 596 · cited 1×
“To address these challenges, we outline the following design suggestions: 5.1.1 Speaker-personalized ASR models for ability-based adaptation.”
Influential
Research works printed but not linked: 3
- Dale J Barr Roger Levy Christoph Scheepers and Harry J Tily. 2013. Random effects structure for confirmatory hypothesis testing: Keep it maximal. Journal of memory and language 68 3 (2013) 255–278. · DOI · Paper page
- Brian MacWhinney. 2021. Tools for Analyzing Talk Part 1: The CHAT Transcription Format. Technical Report. Carnegie Mellon University, Pittsburgh, PA: Carnegie Mellon University. 10.21415/3mhn-0z89 · doi:10.21415/3mhn-0z89
- Jimmy Tobin Phillip Nelson Bob MacDonald Rus Heywood Richard Cave Katie Seaver Antoine Desjardins Pan-Pan Jiang and Jordan R Green. 2024. Automatic speech recognition of conversational speech in individuals with disordered speech. Journal of Speech Language and Hearing Research 67 11 (2024) 4176–4185. · DOI · Paper page
Cited by
AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer’s Disease Care
Yadav, P., Cohn, M., Koppolu, P., Agarwal, H., Gohil, A., Patil, T., Pimento, S. N., & Weakley, A. M. (2026) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase69719.2026.00065
“In the future, we will implement adaptive turn-taking or structured response windows, to improve human-computer interaction and accessibility.”
Self-citationAI Caretaker: An Intelligent Voice-Activated Support System for Dementia Care
Dhingra, A., & Nichols, C. M. (2026) · Cureus · doi:10.7759/cureus.115149
“…to support several characteristics relevant to dementia care, including low-volume speech, incomplete sentences, delayed responses, repeated phrases, and emotionally distressed speech features that are known to challenge automatic speech recognition in older and cognitively impaired speakers [16].”
Metadata
- Authors
- Cohn, M., Lanzi, A., Ishihara, Y., Chuah, C.-N., Zellou, G., & Weakley, A.
- Affiliations
- University of California, Davis (US)
- University of Delaware (US)
- Venue
- Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2026-04-13
- Pages
- 1-23
- OpenAlex
- W7153883810
- Cited by
- 4
- References
- 93
- Citations by year
- 2026: 4
- FWCI
- 35.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Keywords
- speech recognition, cognitive impairment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment. https://app.cochat.ai/papers/10.1145/3772318.3791581
- The paper
- Cohn, M., Lanzi, A., Ishihara, Y., Chuah, C.-N., Zellou, G., & Weakley, A. (2026). Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment. Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3772318.3791581
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.