A Summary of the Research Focus
The National AI Institute for Exceptional Education (AI4ExceptionalEd) is a National Artificial Intelligence (AI) Research Institute led by the University at Buffalo (along with other eight universities) and funded by the National Science Foundation and the Institute of Education Sciences of the US Department of Education. The AI4ExceptionalEd Institute aims to advance AI technologies to help speech language pathologists (SLP), teachers and other professionals to practice at their full potential, ensuring no child in need of speech and language services is left behind. Currently, nearly 3.4 million children, more than half of those served under the Individuals with Disabilities Education Act (IDEA), require speech and language (S&L) services. These children face communication challenges that place them at risk for suboptimal social-emotional and academic outcomes. An alarming shortage of SLPs, combined with delays in identification of needs and unmet services during the COVID- 19 pandemic, has likely exacerbated this gap. The Institute will develop AI technologies complemented by human expertise to inform two innovative solutions: the AI Screener and the AI Orchestrator. The AI Screener is an edge-based solution that will be initially deployed in early childhood classrooms. It will analyze video and audio streams of children’s classroom interactions, derive conventional speech and language measures used by SLPs, and assess novel and hard to obtain automaticity measures. The AI Orchestrator is a superset of the AI Screener with its main application in the public-school classrooms. It will help SLPs, teachers, and other special service providers to administer a wide range of evidence- based interventions and assess their effects on meeting children’s IEP learning targets. At the core of the Orchestrator is a robust multi-agent reinforcement learning framework that can evaluate the potential benefits of different intervention practices and recommend those most appropriate for each child. The development of both AI Screener and AI Orchestrator will be iterative with multiple phases, and we will partner with SLPs, teachers, and other special service providers to ensure our A.I. design process is inclusive with all voices heard.
Practitioners might recommend that pregnant people experiencing stress engage in some mindfulness activities. We also think that practitioners who work with stressed, pregnant people can discuss strategies they could use to improve their stress levels that might also have an effect on their baby. Thus, the caregiver can improve their own emotional health and that of their baby.