ASR-BASED FEEDBACK AND PRONUNCIATION ACCURACY: A QUASI-EXPERIMENTAL STUDY IN PAKISTAN
Keywords:
Affective Filter, Automatic Speech Recognition (ASR), Capt, Corrective Feedback, ESL, Pakistan, Pronunciation Accuracy, Quasi-ExperimentalAbstract
This study investigates the effectiveness of Automatic Speech Recognition (ASR) technology in improving the pronunciation accuracy of English as a Second Language (ESL) learners at a public-sector university in Lahore, Pakistan. Motivated by persistent challenges related to the absence of individualized feedback in large-enrollment classrooms and the documented gap in research addressing Pakistani EFL contexts, the study employs a quasi-experimental mixed-methods design with 40 participants (N = 40) randomly assigned to an experimental group (ASR-based instruction) or a control group (conventional teacher-mediated instruction). Quantitative data were collected at three time points: pre-test, immediate post-test, and delayed post-test, while qualitative data were obtained through semi-structured interviews. Independent samples t-tests, one-way ANOVA, and effect size analysis (Cohen's d) revealed a statistically significant and large-effect advantage for the experimental group (mean gain = 24.25 points; d = 1.45; p < .001). The delayed post-test confirmed superior long-term phonological retention in the experimental group (mean decay = −2.25 vs. −4.15 for the control group). Qualitative analysis yielded three emergent themes: the enabling role of immediate corrective feedback, a marked reduction in speaking anxiety attributable to the non-evaluative nature of ASR, and minor technical concerns about acoustic interference. Grounded in Schmidt’s (1990) Noticing Hypothesis and Krashen’s (1982) Affective Filter Hypothesis, these findings suggest that explicit ASR-based feedback can effectively bridge the input–output gap for ESL learners in the Pakistani higher education context.
.
Downloads
References
Al-Ghamdi, N. (2022). Longitudinal study of CAPT in EFL pronunciation instruction. Journal of Computer Assisted Learning. https://doi.org/10.1111/jcal.12665
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Lawrence Erlbaum Associates.
Krashen, S. D. (1982). Principles and practice in second language acquisition.Pergamon Press. http://www.sdkrashen.com/content/books/principles_and_practice.pdf
Lee, J., & Lee, S. (2023). Evaluating ASR feedback for L2 pronunciation: A focus on common error types. Language Learning & Technology. https://hdl.handle.net/10125/77382
Ngo, T. T.-N., Chen, H. H.-J., & Lai, K. K.-W. (2024). The effectiveness of automatic speech recognition in ESL/EFL pronunciation: A meta-analysis. ReCALL, 36(1), 4–21. https://doi.org/10.1017/S0958344023000113
O'Brien, M. G. (2021). Teaching and learning pronunciation with technology: Current possibilities, pedagogical recommendations, and directions for the future. The Modern Language Journal, 105(1), 232–251. https://doi.org/10.1111/modl.12689
Schmidt, R. W. (1990). The role of consciousness in second language learning. Applied Linguistics, 11(2), 129–158. https://doi.org/10.1093/applin/11.2.129
Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Houghton Mifflin.
Underwood, J. (2024). Artificial intelligence in language education. Routledge. https://doi.org/10.4324/9781003362142
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Syeda Noor Fatima, Sadia Ghaffar, Sidra Bukhari, Dr. Tayyaba Yasmin (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
