Our sessions at Virtual ISAAC 2025
Let’s look before we leap: a thoughtful approach to AI and AAC
Presenters: Alyssa Zisk and David Niemeijer
Date: Wednesday, October 29 | Time: 8:30 AM - 9:30 AM EDT
“Artificial Intelligence,” or AI, is a hot topic in the world and specifically in AAC – but “AI” implementations vary widely. We will identify different types of “AI,” their uses in AAC, and considerations around these uses. The uses of machine learning techniques for brain-computer interfaces, personal voices, and large language models (LLMs) differ – but all fall under “AI” and all have potential applications to AAC. By addressing these cases separately, we identified key considerations.
First, we consider authenticity. Professionals express concerns about authorship: LLMs may alter or invent content. AAC users have concerns about message style and tone (Valencia et al., 2023) but also about undue judgment regarding authorship (Holyfield & Williams, 2025). Also in the area of authenticity, some AAC users and their families are excited by the idea that they can have a voice that sounds like their voice (or a guess at what their voice would be.) Others question if this should even be the goal, or about this becoming an expectation rather than an option (Preece et al., 2024).
Second, we consider privacy. “AI” models often involve cloud processing in their creation, adaptation, and/or use. This has trade-offs with authenticity: models tuned with specific user data (neural signals, audio, or text output) can be more effective and authentic, but they then include that data and may reveal it in unintended ways (Valencia et al., 2023).
Third, we consider barriers to learning. A literate user can check LLM-generated text and make decisions about speed, effort, and tone. However, much like calculator use elides the math skills to effectively use a calculator, LLM use elides the language skills to check and edit LLM output.
Finally, we consider availability and accessibility – some applications of “AI” are becoming ubiquitous. Others may be touted as the future of AAC while remaining inaccessible (e.g. voice banking, Preece et al., 2024) or rarely available (e.g. brain computer interfaces, Sellwood et al., 2024).
Addressing “AI” in AAC effectively involves considering each of its use cases on its own merits. It also involves addressing these considerations – not as issues unique to the intersection of AAC and AI, but as applications of broader issues to this intersection.
Bridging evidence-based feature-matching with a "single preferred AAC system" within schools
Presenters: Erin Sheldon and Willemijn Wetzels
Date: Wednesday, October 29 | Time: 9:30 PM - 10:30 PM EDT
The long-standing process of feature matching is intended to ensure that we take an evidence-based approach to selecting the AAC system that is the best fit for a user's skills and needs. In recent years, the individual feature-matching process has been presented in opposition to the increasingly common practice of a "single preferred system" for AAC implementation within school systems (Senner et al., 2025). The "single preferred system" approach is intended to address the needs of the communication partners and systems who provide AAC to emergent students as part of an educational program. This single system approach recognizes that school personnel need the opportunity to become fluent in navigating and using AAC systems in order to provide quality interventions such as aided language
input. Communication partners and educational environments struggle to provide high-quality AAC intervention when every emergent student has a unique AAC system even when this is not needed. The single preferred system approach is often justified by framing it within the Multi-Tiered Systems of Support (MTSS). However, this approach can result in what opponents describe as "one-size-fits-all" AAC, where the vast majority of students are provided with a single AAC app and vocabulary that may be insufficient or inappropriate for many users.
This session will question whether individual feature matching is truly in opposition to a single preferred system. Instead, we will suggest that the tension between these two approaches is a false dichotomy, resulting from a too-narrow approach to feature-matching or a too-loose approach to a single preferred system. A narrow approach to feature-matching focuses so closely on the uniqueness of the individual student and their current access needs that it risks missing the universality of what all emergent AAC users require: access to the dominant language(s) of their environments, with high quality support from communication partners who can facilitate long-term AAC adoption, meeting the user's needs both now and in the future. A too-loose approach to "single preferred systems" risks providing the AAC that is most convenient or affordable to partners or to educational systems without sufficient consideration of the individual user's current and long-term needs. Further, many claims that a single preferred system are based in MTSS reflect misconceptions and partial understanding of MTSS, such as ignoring the need to plan the accompanying Response to Intervention that is foundational to MTSS.
This session will propose that a broader approach to feature matching is needed to move this discussion forward. We will ground our discussion in Schlosser et. al's (2006) proposed PESICO framework for feature matching. PESICO is an evidence-based approach to consider the complex ecosystem of needs that require a strong AAC feature match: the individual student, the learning environment, such as the classroom; stakeholders, such as classroom educators, educational assistants and families; and the demands of the intervention, such as aided language input. PESICO provides clinicians with a framework for how to compare the relative strengths and weaknesses of a range of AAC solutions, in order to select the system(s) that will result in the best outcomes for the user. We will position the needs of AAC users within the tiered intervention opportunities of MTSS, and will discuss the screening, progress monitoring and data collection inherent to Response to Intervention. Participants will leave the session with confidence that they can apply evidence-based practice to selecting and implementing AAC systems, even within school systems that benefit from a common AAC approach across users.
AAC as a Tool for Feelings, Regulation and Problem Solving
Presenter: Amanda Hartmann
Date: Wednesday, October 29 | Time: 11:00 PM EDT
Often people who use AAC are only supported to express very basic feelings - happy, sad and maybe angry. How we feel is far more complex. In addition, sometimes these feelings are taught in a way that is ineffective and unhelpful. We need to do more for AAC users!
Why is this so important? We all need to be able to express how we feel. We need to understand our inner body signals that helps us understand our emotions (Interoception). Expressing emotions and having these understood by the people around you, make us feel understood and heard. This increases the opportunities for connections. Additionally, when we can express our feelings, it helps us to start to discover and communicate what we need to feel better. Nonspeaking people need all of these opportunities and experiences.
So what can we do? In this workshop we will dive into new ideas and strategies for supporting emotions, regulation and problem solving for people who are nonspeaking.
