Authors:
Ezgi Demir, S. Rubin Bose, Mouhamadou Fall, Cao Siyu, Li Chengru, Ankan Basak

Addresses:
Department of Artificial Intelligence, Lancaster University, Lancaster, Lancashire, England, United Kingdom. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Intelligent Transportation Systems, LITIS - IT Laboratory, Information Processing and Systems, University of Rouen Normandy, Mont-Saint-Aignan, Normandy, France. Department of Computing and Information Systems, Singapore Management University, Basah, Singapore. Department of Information and Communication Engineering, The University of Tokyo, Bunkyo-ku, Tokyo, Japan. Department of Computational Science and Engineering, McMaster University, Hamilton, Ontario, Canada.

Abstract:

The paper describes a pronunciation feedback and exercise-generation tool designed to enhance language acquisition through real-time phoneme analysis. The system evaluates the correctness of a student's pronunciation using cutting-edge speech recognition and Generative AI (GenAI) technologies, then creates customised exercises to address particular phonetic issues. The method combines a simple UI that lets students engage with the system and get immediate speech feedback. The system identifies differences between the target and spoken pronunciation by analysing the phonemic structure of the learner's utterances and provides insights into error patterns. These ideas then inform tailored exercises designed to strengthen troublesome phonemes. GenAI in the system enables adaptive learning, in which exercise difficulty and emphasis change based on the student's development. This adaptive strategy ensures the system can support students at different skill levels. The findings suggest that consistent, data-driven practice can significantly improve pronunciation, enabling more efficient and accessible language acquisition. This paper examines the system's design, implementation, and potential impact on contemporary language teaching.

Keywords: Speech Therapy; Speech-Language Pathology (SLP); Speech Disorder; Adaptive Strategy Guarantees; Data-Driven Practice; Contemporary Language Teaching.

Received on: 12/07/2025, Revised on: 23/09/2025, Accepted on: 20/10/2025, Published on: 03/06/2026

DOI: 10.69888/FTSBE.2026.000789

FMDB Transactions on Sustainable Biomedical Engineering, 2026 Vol. 1 No. 2, Pages: 73-85

• Views : 22
• Downloads : 7

Download PDF