Adopting AI-Based Speech Recognition for Enhancing Pronunciation Accuracy and Learner Confidence

Abstract

This study examines the integration of AI–based speech recognition (ELSA Speak, Speechling) in a language centre and its effects on pronunciation accuracy and learner confidence. Two groups of intermediate EFL learners (N = 40) completed pre-test and post-test diagnostic pronunciation assessments, with the experimental group receiving support through AI-app usage analytics. The comparative results revealed that the AI-assisted group demonstrated significantly more positive outcomes than the control group (p < .001), thus achieving higher post-test scores and increased learner confidence in the pronunciation assessment in the experimental group (paired t, p < .001). Consistent engagement in AI-assisted pronunciation practice was associated with improved performance (r = .62, p < .01). Quantitative results showed that learners using AI tools achieved higher pronunciation scores and confidence, while qualitative findings indicated reduced speaking anxiety, sustained motivation, and enhanced learner autonomy, despite minor implementation challenges such as connectivity issues and occasional feedback perception mismatches. The findings show the effective integration of AI-based pronunciation tools with conventional language instruction through feedback and self-regulated learning scaffolds. However, the intact–class design, single-centre context, and short duration result in limiting generalizability, demanding a longitudinal, multi-site replication.

Conflict of Interest: The authors declare that there are no conflicts of interest related to the research, authorship, and/or publication of this article, and that the data presented have not been fabricated or falsified.

Funding: This research did not receive any specific grant or financial support from public, commercial, or not-for profit funding agencies.

Participant Consent:  The authors confirm that Informed consent was obtained from all participants, and confidentiality was duly maintained.

Data Fabrication/Falsification Statement: The authors declare that no data have been fabricated, falsified, or manipulated in this study.

Copyright: Copyright (c) 2025 Rehana Gulzar & Muhammad Ehsan