Co-Designing QuickPic: Automated Topic-Specific Communication Boards from Photographs for AAC-Based Language Instruction
Abstract
Traditional topic-specific communication boards for Augmentative and Alternative Communication (AAC) require manual programming of relevant symbolic vocabulary, which is time-consuming and often impractical even for experienced Speech-Language Pathologists (SLPs). While recent research has demonstrated the potential to automatically generate these boards from photographs using artificial intelligence, there has been no exploration on how to design such tools to support the specific needs of AAC-based language instruction. This paper introduces QuickPic, a mobile AAC application co-designed with SLPs and special educators, aimed at enhancing language learning for non-speaking individuals, such as autistic children. Through a 17-month design process, we uncover the unique design features required to provide timely language support in therapy and special education contexts. We present emerging evidence on the overall satisfaction of SLPs using QuickPic, and on the advantages of large language model-based generation compared to the existing technique for automated vocabulary from photographs for AAC.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
GenAI tools can support students with special education requirements.
“support students with special education requirements”
From Generative AI in Language Education: Bridging Divide and Fostering Inclusivity (2025) · cites this paper as De Vargas et al., 2024
GenAI can cater to special education requirements, enhancing inclusivity.
“Alenizi et al.'s (2023) and De Vargas et al.'s (2024) studies demonstrate how GenAI can cater to special education requirements, enhancing inclusivity.”
From Generative AI in Language Education: Bridging Divide and Fostering Inclusivity (2025) · cites this paper as De Vargas et al., 2024
Cites
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · see citing works
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · see citing works
The mHealth App Usability Questionnaire (MAUQ): Development and Validation Study
Zhou, L., Bao, J., Setiawan, I. M. A., Saptono, A., & Parmanto, B. (2019) · JMIR mHealth and uHealth · doi:10.2196/11500 · Cited by 675 · cited 2× · see citing works
“The frst questionnaire was the Mobile-health App Usability Questionnaire (MAUQ [57]), a psychometrically validated instrument to capture users perception of the usefulness and usability of health applications, including those for therapeutic and education purposes 6 .”
BackgroundMethodInfluentialEngaging older people using participatory design
Lindsay, S., Jackson, D., Schofield, G., & Olivier, P. (2012) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2207676.2208570 · Cited by 323 · see citing works
Valencia, S., Cave, R., Kallarackal, K., Seaver, K., Terry, M., & Kane, S. K. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581560 · Cited by 97 · cited 2× · see citing works
“Notably, most participants in the Valencia et al. [51]’s work found that a prompt-based generation of sentences from single words to be "very or extremely useful", potentially helping them to create requests for routine, self-care and accessibility related tasks in a daily basis.”
BackgroundTowards Improving Predictive AAC using Crowdsourced Dialogues and Partner Context
Vertanen, K. (2017) · Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3132525.3134814 · Cited by 10 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Generative AI in Language Education: Bridging Divide and Fostering Inclusivity
Weng, Z., & Fu, Y. (2025) · International Journal of Technology in Education · doi:10.46328/ijte.1056 · Cited by 31 · see citing works
“Two studies (Alenizi et al., 2023; De Vargas et al., 2024) explored how GenAI can support special education students in language learning.”
- Authors
- Fontana De Vargas, M., Yu, C., Shane, H. C., & Moffatt, K.
- Affiliations
- McGill University, Canada
- Boston Children's Hospital (US)
- McGill University (CA)
- Venue
- Proceedings of the CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2024-05-11
- Pages
- 1-16
- OpenAlex
- W4396833434
- Cited by
- 30
- References
- 6
- Citations by year
- 2026: 15 · 2025: 12 · 2024: 3
- FWCI
- 26.86
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- eScholarship@McGill (McGill) (submittedVersion)
- Funders
- Fonds de recherche du Québec – Nature et technologies
- Natural Sciences and Engineering Research Council of Canada (rgpin-2018-06130)
- AGE-WELL
- Canada Research Chairs
- National Institute on Disability and Rehabilitation Research (90dphf0004)
- Topics
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
- Keywords
- augmentative and alternative communication, communication boards, photographs, large language models, co-design, speech-language pathologists, special education, children with autism
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
