Helping or Homogenizing? GenAI as a Design Partner to Pre-Service SLPs for Just-in-Time Programming of AAC

2025-07-29

AI Summary

Visual Scene Displays (VSDs) are critical augmentative and alternative communication (AAC) tools for nonspeaking autistic children, yet their manual creation is time-intensive and requires specialized expertise, limiting accessibility for pre-service speech-language pathologists (SLPs). Method: This study pioneers the integration of generative AI into VSD authoring by automating interactive hotspot detection in images and embedding human-AI co-design principles to rapidly generate developmentally appropriate VSD content. Contribution/Results: Experimental evaluation demonstrated significant reductions in VSD creation time and increased user confidence among pre-service SLPs. However, findings also revealed risks of overreliance on AI-generated suggestions and homogenization of hotspot content. The work empirically validates generative AI’s potential to enhance accessibility in assistive technology while surfacing the inherent tension between automation and personalization. It provides methodological insights and evidence-based guidance for ethically grounded, clinically informed AAC design and pre-service SLP training.

Technology Category

• Humans and AI: AI for Accessibility
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Augmentative and alternative communication (AAC) devices are used by many people around the world who experience difficulties in communicating verbally. One AAC device which is especially useful for minimally verbal autistic children in developing language and communication skills are visual scene displays (VSD). VSDs use images with interactive hotspots embedded in them to directly connect language to real-world contexts which are meaningful to the AAC user. While VSDs can effectively support emergent communicators, their widespread adoption is impacted by how difficult these devices are to configure. We developed a prototype that uses generative AI to automatically suggest initial hotspots on an image to help non-experts efficiently create VSDs. We conducted a within-subjects user study to understand how effective our prototype is in supporting non-expert users, specifically pre-service speech-language pathologists (SLP) who are not familiar with VSDs as an AAC intervention. Pre-service SLPs are actively studying to become clinically certified SLPs and have domain-specific knowledge about language and communication skill development. We evaluated the effectiveness of our prototype based on creation time, quality, and user confidence. We also analyzed the relevance and developmental appropriateness of the automatically generated hotspots and how often users interacted with the generated hotspots. Our results were mixed with SLPs becoming more efficient and confident. However, there were multiple negative impacts as well, including over-reliance and homogenization of communication options. The implications of these findings reach beyond the domain of AAC, especially as generative AI becomes more prevalent across domains, including assistive technology. Future work is needed to further identify and address these risks associated with integrating generative AI into assistive technology.

Problem

• Automating hotspot suggestions for AAC visual scene displays
• Evaluating GenAI's impact on non-expert VSD creation efficiency
• Assessing risks of over-reliance on AI-generated AAC content

Innovation

• Generative AI suggests initial image hotspots
• Prototype aids non-experts in VSD creation
• Evaluated hotspot relevance and user interaction