Artificial Intelligence for EFL Students' Listening Skills

Abstract

Text-to-Speech is an AI product that involves artificially producing human speech by converting text into voice using a speech synthesizer. The role of AI in ESL and EFL language instruction has been studied since 2010. However, to the best of the authors' knowledge, research on the effectiveness of text-to-speech-based (TTS) e-modules in enhancing the listening skills of EFL students in Indonesia is still limited. The aim of this study is to investigate the impact of Text-to-Speech-based e-modules (TTS e-modules) on the listening skills of EFL students in Indonesia. The TTS e-module was designed using the R & D research approach with the ADDIE model. The samples were 60 seventh-grade students of junior high school in Tasikmalaya, Indonesia. During the evaluation phase, a pre-post quasi-experiment was conducted. The findings, evaluated using the 100-point scale, indicate below-average pre-test mean scores for both the control group (41.87) and the experimental group (37.87). After the intervention (using a TTS e-module for one semester / 14 classroom sessions x 90 minutes), the mean for the control group was 52.13, while that of the experimental group mean score increased to 69.93. The independent sample t-test scores confirmed significant differences in achievement, as indicated by the p-value of 0.000< 0.05. This indicates that the null hypothesis was rejected. Positive student evaluations of the e-module further support the study's findings. The study concludes that the TTS e-module significantly improved the listening abilities of the participants. This research has implications for educators, students, and future scholars, and provides valuable insights into the innovative use of technology for language learning.