Ikkyu Choi is a Managing Senior Research Scientist at ETS Research Institute, where he leads a research program dedicated to the valid, reliable, and fair use of AI for assessment. He holds a Ph.D. in Applied Linguistics from the University of California, Los Angeles. His research leverages statistical models, machine learning algorithms, and natural language processing techniques to develop automated item generation capabilities and bring about associated content workflow innovations. He has published widely across multiple disciplines and received the 2019 Best Article Award from the International Language Testing Association (ILTA). He has also served on various ILTA committees and on the editorial advisory board of the NCME Instructional Topics in Educational Measurement Series. He is currently serving as an associate editor of Language Assessment Quarterly.
Speech Processing and Analysis with Foundation Models for Applied Linguistics Research and Practice
Pre-Conference Workshop Abstract
Oral communication is a fundamental area of study with wide-ranging applications in language learning, teaching, and assessment. Effectively investigating and utilizing spoken language requires the ability to process and analyze data stored in digital audio formats. As storage and computational resources become more accessible, speech processing is increasingly powerful and efficient. Recent advances in foundation language models have further expanded the possibilities for speech-related research and applications. These models offer robust capabilities for a variety of downstream tasks, making sophisticated speech analysis more accessible to researchers and practitioners.
This full-day workshop introduces the core concepts and practical techniques of speech processing and analysis. The morning session will focus on the fundamentals of acoustic phonetics and digital signal processing, with hands-on training to visualize and quantify key acoustic features. In the afternoon, participants will explore how to apply foundation models to real-world tasks such as automatic speech recognition (ASR), text-to-speech synthesis, and automated speech evaluation. Using open-source tools, participants will work with real-world datasets to implement these techniques in practice. By the end of the workshop, participants will have developed both a conceptual understanding and practical skills in speech processing and analysis to enhance and expand their research and professional practice.
Date & Time: Thursday September 25, 2025 | 9:00 AM – 4:00 PM
Cost: $65 per person
Link to the registration page