DEMO: EaseTalk: An LLM-driven speech practice tool for real-life scenarios
Loading...
Files
Accepted Version
Date
2025-07-03
Authors
Faggiani, Marco
Qirtas, Malik Muhammad
Frizelle, Pauline
Ryan, Fiona
Muller, Nicole
Visentin, Andrea
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published Version
Abstract
Stuttering can make everyday conversations challenging, especially in situations that involve unfamiliar people or social pressure. While traditional therapy provides structured support, many individuals struggle to apply those techniques in real-world scenarios. Digital speech tools exist, but most focus on repetitive drills and rarely provide realistic, contextdriven speaking practice. We present EaseTalk, an AI-driven mobile application that allows users to practice real-life conversational scenarios in a supportive, self-paced environment. The app uses speech recognition and prompt-engineered large language models (LLMs) to detect speech disfluencies such as repetitions, prolongations and blocks. EaseTalk aims to empower users through independent, scenario-based speech practice with potential applications extending beyond stuttering into areas like social anxiety, interview preparation and language learning.
Description
Keywords
Stuttering , Stammering , Speech therapy , Large language models , Mobile application
Citation
Faggiani, M., Qirtas, M. M., Frizelle, P., Ryan, F., Muller, N. and Visentin, A. (2025) 'DEMO: EaseTalk: An LLM-driven speech practice tool for real-life scenarios', 2025 IEEE International Conference on Smart Computing (SMARTCOMP), Cork, Ireland, 16-19 June 2025, pp. 246-248. https://doi.org/10.1109/SMARTCOMP65954.2025.00045