The National AI Institute for Exceptional Education
Silver Lining for Learning
Navigating Educational Needs with AI
This chapter delves into the challenges of diagnosing educational needs, particularly in students with speech language disorders. It highlights the use of AI technologies and evidence-based practices to enhance diagnosis, focusing on methodologies like the Sean Redmond Sentence Recall for assessing language impairments. The discussion also covers the integration of automatic speech recognition in educational settings, comparing AI evaluations with human assessments to refine speech interventions.
The National AI Institute for Exceptional Education with Jinjun Xiong, Sean Redmond, and Dancheng Liu
Nearly 3.4 million children require speech and language services under the Individuals with Disabilities Education Act (IDEA) and are at risk of falling behind in their academic and social-emotional development without timely intervention by Speech and Language Pathologists (SLPs). Unfortunately, there is a significant shortage of SLPs and the COVID pandemic has further exacerbated this gap, making it almost impossible for SLPs to provide individualized services for children. The National AI Institute for Exceptional Education (AI4ExceptionalEd) aims to close this gap by developing advanced AI technologies to scale SLPs’ availability and services such that no child in need of speech and language services is left behind. Towards this end, the Institute proposes to develop two novel AI solutions: (1) the AI Screener to enable universal early screening for all children, and (2) the AI Orchestrator to work with SLPs and teachers to provide individualized interventions for children with their formal Individualized Education Program (IEP).
In this podcast, Dr. Jinjun Xiong, the Scientific Director of the Institute, will discuss one of the many projects going on at the Institute. The project is called AutoRSR, led by the Institute’s PhD student Mr. Dancheng Liu. AutoRSR aims to leverage the power of AI to automate an evidence-based screening method developed by an SLP expert, Dr. Sean Redmon. Evidence-based early screening for children with speech and language challenges is critically important as it provides opportunities for those impacted children to receive diagnostics early and hence the needed invention. But conducting screening instruments is typically time-consuming and requires specialized training for those who conduct the screening. Can we leverage the power of AI to automate some of those screening processes so that more children can receive such a screening test? What would be some of the research challenges and capability gaps in developing such a solution? What are some of the dos and don’ts of carrying out such interdisciplinary research? Through this podcast’s discussion about the AI4ExceptionalEd Institute and the development of the AutoRSR project, we hope to shed some light on those questions.
More resources and information about our guests below the video
https://youtu.be/ollQZW7JID8
Readings and Resources:
Hadley, P. A., & Xiong, J. Researchers Partner on AI to Free Up SLPs for Direct Services. https://leader.pubs.asha.org/do/10.1044/leader.FTR1b.28092023.AI-ethics-slp-aud.50/full The ASHA LeaderLive, 2023.
Episode Guests
Jinjun Xiong
Dr. Jinjun Xiong is an Empire Innovation Professor with the Department of Computer Science and Engineering at the University at Buffalo (UB). He also serves as the Scientific Director for the $20 M National AI Institute for Exceptional Education (http://ai4exceptionaled.org), Director for the SUNY-UB Institute for Artificial Intelligence and Data Science (https://www.buffalo.edu/ai-data-science.html), and the AI Thrust Lead for the $10M National Center for Early Literacy and Responsible AI (CELaRAI). Prior to UB, he was a Senior Researcher and Program Director for AI and Hybrid Clouds Systems at the IBM Thomas J. Watson Research Center. He was the former co-founder and co-director of the IBM-Illinois Center for Cognitive Computing Systems Research (C3SR), the success of which in 5 years has led to the 10-year $200M expansion of the center to the IBM-Illinois Discovery Accelerator Institute. His research interests are in across-stack AI systems research, including AI applications, algorithms, tooling, and computer architectures.
Professor Sean M. Redmond is a Fellow of the American Speech Language and Hearing Association and Board-Certified Specialist in Child Language. Dr. Redmond received his PhD from the University of Kansas in 1998 and joined the faculty at the University of Utah shortly thereafter. He has over 45 peer-reviewed publications as well as book chapters on the topics of pediatric language disorders, socioemotional behavioral disorders, and differential diagnosis. His scholarship has been funded by the National Institutes of Health. Dr Redmond has served as Editor in Chief for the Journal of Speech, Language, and Hearing Research and is a founding member of the website https://dldandme.org/
Dancheng Liu is a PhD student in the Computer Science and Engineering Department at the University at Buffalo, where he is also affiliated with the National AI Institute for Exceptional Education. Before joining UB, he completed both his bachelor’s and master’s degrees at the University of California, San Diego. His current research explores the intersection of AI and speech-language pathology, with a particular focus on advancing AI technologies to scale the availability of speech-language pathologists. He aims to create innovative tools to streamline SLPs’ tasks with state-of-the-art deep learning models and advanced algorithms. He led the development of AutoRSR which enables fully automated Redmond Sentence Recall assessments, allowing the entire process to be automated, opening up the potential for enabling universal speech disorder screening in the future.
Remember Everything You Learn from Podcasts
