Developing a Learning Platform to Support Minimally Verbal Individuals with Autism
openNIDCD - National Institute on Deafness and Other Communication Disorders
PROJECT SUMMARY / ABSTRACT
Many children with autism spectrum disorder (ASD) remain minimally verbal beyond early childhood despite
intensive services. For these families, options often don’t fit daily life: augmentative and alternative
communication (AAC) apps are hard to personalize and rely on context-poor static symbols, while video
modeling requires filming and editing—slow, costly steps that limit generalization and home use. Caregivers,
therefore, struggle to deliver frequent, motivating practice tailored to real routines. Our proposed solution, Young
Speaker, an iOS-compatible software platform, is intended to tackle these barriers by unifying two well-supported
ideas: video modeling and AAC, into a single workflow that creates highly personalized practice materials in
minutes. Caregivers select goals tied to everyday routines (e.g., “more juice,” “go outside”), and the app uses an
easy avatar creator, templated social stories, and AI-assisted prompts to produce short, child-relevant videos
and practice sequences featuring the child’s own avatar and familiar settings, representing the key innovative
features of our approach. A lightweight dashboard tracks use, goal attempts, and responses to support data-
informed adjustments while keeping privacy protections front and center.
STTR Phase I will deliver an iPad/web prototype of Young Speaker with core features (goal-setting tools, avatar
creation, and content builders) and conduct two formative evaluations. First, a lab-based usability cycle with
approximately 15 parent caregivers/educators will identify pain points and drive rapid refinements using standard
usability scales and brief interviews. Second, a one-month home feasibility study with about 15 parent–child
dyads (elementary-age, minimally verbal) will examine feasibility, acceptability, and real-world engagement:
families will complete onboarding, create at least one avatar and practice content, and run 10–15 minute
sessions twice daily during natural routines. App analytics (dose and content created), brief pre-/post-
questionnaires, and exit interviews will inform product fit, caregiver workflow, and measurement procedures for
a subsequent Phase II efficacy trial.
The expected deliverables are an optimized prototype, evidence of feasibility and acceptability, finalized user
and outcome measures, and a clear plan for Phase II testing. By lowering production burden and elevating
personal relevance, Young Speaker aims to empower caregivers and educators to provide frequent, motivating
practice that supports meaningful gains in functional communication at home and school, with a
commercialization pathway through school-district licensing, direct-to-consumer offerings, and Medicaid waiver
channels. Young Speaker will be marketed as an educational/skill-building tool (no diagnosis/treatment claims)
and is not expected to require FDA premarket review; if future versions add speech-generating device
capabilities or therapeutic claims, we will pursue the appropriate Class II pathway (e.g., 510(k)/De Novo) in
consultation with FDA.
Up to $313K
health research