JALT2025 - Tokyo

Training Listening and Speech with AI-Enhanced Audio Tools

Nov 1, 2025, 1:20 PM

30m

National Olympics Memorial Youth Center / 国立オリンピック記念青少年総合センター

Practice-oriented Workshop (30-minutes) Technology Room 506

Speakers

Robert Cvitkovic (Teikyo University) Omar Massoud (Meiji Gakuin University) Yoko Kita (Kyoto Notre Dame University)

Description

This workshop explores how instructors can use AI assistants to create level-appropriate audio materials to train speaking skills. Participants will evaluate synthetic speech for phonetic accuracy, comprehensibility, and naturalness, then learn prompt-engineering strategies to enhance output quality. Attendees will leave with practical guidelines and up-to-date information about incorporating AI-generated audio task materials into their speaking and listening classes.

Summary

This workshop explores how instructors can use AI assistants to create level-appropriate audio materials to train speaking skills. Participants will evaluate synthetic speech for phonetic accuracy, comprehensibility, and naturalness, then learn prompt-engineering strategies to enhance output quality. Demonstrations cover using the International Phonetic Alphabet (IPA) to refine targeted pronunciation features. Attendees will leave with practical guidelines and up-to-date information about incorporating AI-generated audio task materials into their speaking and listening classes.