THE IMPACT OF AI-POWERED SPEECH RECOGNITION TOOLS ON PRONUNCIATION ACCURACY IN EFL UNIVERSITY LEARNERS
Keywords:
Keywords: AI-powered speech recognition, EFL speaking instruction, pronunciation accuracy, learner autonomy, higher education, Central AsiaAbstract
Abstract: This study investigates the effects of integrating AI-powered speech recognition (ASR) tools into university-level English as a Foreign Language (EFL) speaking instruction. Using a mixed-methods design, data were collected from 118 undergraduate students across two intact groups at a state university in Uzbekistan over one academic semester (16 weeks). The experimental group (n = 59) used ASR-based speaking practice sessions three times per week as a supplement to regular instruction, while the control group (n = 59) followed a conventional teacher-led speaking curriculum. Pre- and post-test scores on the English Pronunciation Scale (EPS) and the Communicative Speaking Assessment Rubric (CSAR) were used to measure pronunciation accuracy and overall oral proficiency. Findings revealed a statistically significant improvement in vowel articulation, word stress, and connected speech in the ASR group (p < .01), while improvements in the control group were modest and largely limited to segmental features. Qualitative analysis of learner interviews and speaking journals identified reduced anxiety, increased self-monitoring behavior, and a stronger sense of speaking autonomy as key psychological benefits. The study also revealed several constraints: overreliance on the tool's feedback, lower motivation among intermediate proficiency learners, and inconsistencies in ASR recognition of regionally accented English. Pedagogical implications are discussed, including teacher readiness, tool selection criteria, and a proposed integration framework for EFL speaking classrooms.References
1. Bajorek, J. P. (2019). Voice recognition still has significant race and gender biases. Harvard Business Review. Retrieved from https://hbr.org
2. Brazil, D. (1994). Pronunciation for advanced learners of English. Cambridge University Press.
3. Chapelle, C. A. (2010). The spread of computer-assisted language learning. Language Teaching, 43(1), 66–74.
4. DeKeyser, R. (2015). Skill acquisition theory. In B. VanPatten & J. Williams (Eds.), Theories in second language acquisition (2nd ed., pp. 94–112). Routledge.
5. Derwing, T. M., & Munro, M. J. (2015). Pronunciation fundamentals: Evidence-based perspectives for L2 teaching and research. John Benjamins.
6. Fryer, L. K., Ainley, M., Thompson, A., Gibson, A., & Sherlock, Z. (2017). Stimulating and sustaining interest in a language course: An experimental comparison of chatbot and human task partners. Computers in Human Behavior, 75, 461–468.
7. Golonka, E. M., Bowles, A. R., Frank, V. M., Richardson, D. L., & Freynik, S. (2012). Technologies for foreign language learning: A review of technology types and their effectiveness. Computer Assisted Language Learning, 27(1), 70–105.
8. Holec, H. (1981). Autonomy and foreign language learning. Pergamon Press.
9. Horwitz, E. K., Horwitz, M. B., & Cope, J. (1986). Foreign language classroom anxiety. Modern Language Journal, 70(2), 125–132.
10. Karpinska-Musiał, B. (2015). Intercultural education in higher education contexts: Challenges in post-Soviet spaces. Journal of Intercultural Communication, 38, 1–14.
