CoChat

Generative AI applied to AAC for aphasia: a pilot study of Aphasia-GPT

The DOI matches its Crossref record, with a small difference in title or year; 29 of the 29 references it cites were found in a registry or an index.

Abstract

Background People with aphasia may be supported by augmentative and alternative communication systems, but further development is necessary to improve the communication support such systems provide. Advances in artificial intelligence methods of natural language processing may provide improved support for people with aphasia, but development and testing involving people with aphasia is critical.Aims The purpose of the study is to describe the development and pilot testing of a new AAC system for people with aphasia, a mobile web app named Aphasia-GPT.Methods & Procedures Aphasia-GPT is specifically designed to receive spoken input from a user with aphasia; it then provides a list of suggested or predicted utterances that are well-formed while still based on the disordered input. Three participants with aphasia participated in language sampling with and without the support of the system. Outcomes of the support provided by the system were qualitatively summarized and described. The participants were also interviewed for their perspectives on the system.Outcomes & Results Results from the pilot test of the Aphasia-GPT system in three people with moderate aphasia suggested its current form may best serve as a sentence production aid for those with non-fluent aphasia and relatively few phonemic paraphasias or apraxic errors. Results also revealed areas for future improvement, including handling of less intelligible speech and providing applicable suggestions for a broader array of communication scenarios.Conclusions User feedback and clinical observations support further development of the system to enhance communication for a broader range of profiles and communication tasks.

Overview

Integrity signals

Registry

Crossref · 10.1080/02687038.2024.2445663

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 29 references

Research works printed but not linked: 2

  1. Beukelman, D. R., & Light, J. C. (2020). Augmentative & alternative communication: Supporting children and adults with complex communication needs (5th ed.). Paul H. Brookes Publishing Co.
  2. (2024). IAP2 public participation pillars. International Association for Public Participation. https://www.iap2.org/page/pillarsIAP2.

Cited by

See all 13

Metadata

Authors
Bailey, D. J., Herget, F., Hansen, D., Burton, F., Pitt, G., Harmon, T., & Wingate, D.
Affiliations
  • Brigham Young University (US)
  • The University of Texas at Dallas (US)
  • Inc
  • Digital Room, LLC
Corresponding author
Bailey, Dallin J.
Venue
Aphasiology
Published
2024-12-31
Volume
40
Issue
1
Pages
150-165
ISSN
  • 0268-7038 (ISSN-L)
  • 1464-5041
OpenAlex
W4405944507
Cited by
13
References
29
Citations by year
2026: 9 · 2025: 4
FWCI
11.02
Type
journal article
Language
en
Open access
closed
Locations
  • Aphasiology (publishedVersion)
  • ScholarsArchive (Brigham Young University) (submittedVersion)
Funders
Simmons Research Endowment at Brigham Young University
Topics
  • Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
  • Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
Keywords
aphasia, augmentative and alternative communication, generative AI, speech-to-text, non-fluent aphasia, speech intelligibility, user perspective, mobile web application

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: Generative AI applied to AAC for aphasia: a pilot study of Aphasia-GPT. https://app.cochat.ai/papers/10.1080/02687038.2024.2445663
The paper
Bailey, D. J., Herget, F., Hansen, D., Burton, F., Pitt, G., Harmon, T., & Wingate, D. (2026). Generative AI applied to AAC for aphasia: a pilot study of Aphasia-GPT. Aphasiology. https://doi.org/10.1080/02687038.2024.2445663

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.