The increasing integration of Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) in language learning has created new opportunities for improving Arabic listening instruction. However, previous studies have primarily focused on the technical effectiveness of these technologies and learning outcomes, while limited attention has been paid to learners' responses and the adaptive learning strategies that emerge during technology-mediated learning. This study investigates learners' responses and adaptive strategies when using an interactive web-assisted learning environment integrating ASR and TTS in Arabic listening instruction. A qualitative case study was conducted with 28 secondary school students in Malaysia over eight instructional sessions. Data were collected through questionnaires, semi-structured interviews, classroom observations, field notes, and learning activity records, and were analysed using the Miles and Huberman interactive model. The findings reveal that learners demonstrated positive responses, reflected in increased motivation, active engagement, and improved listening comprehension. They also developed adaptive strategies, including repeated audio playback, integrating visual and auditory information, and independently utilizing automated feedback to improve pronunciation and comprehension. The study contributes to the literature on Computer-Assisted Language Learning (CALL) by demonstrating that the pedagogical integration of ASR and TTS supports adaptive learning behaviours and learner autonomy. Furthermore, it extends the application of Cognitive Load Theory by showing how multimodal feedback can facilitate more meaningful and learner-centred Arabic listening instruction.
Copyrights © 2026