Edtech and pronunciation training: how speech recognition software aids ESL learners

Abstract

Pronunciation training has long been challenging in learning English as a Second Language (ESL). Integrating speech recognition software into pronunciation teaching, learning, and assessment has revolutionized traditional approaches and empowered learners to take control of their learning. This study explores the role of Automatic Speech Recognition (ASR) in aiding ESL learners in developing accurate pronunciation. Drawing from key research in the field, including studies by Pennington & Rogerson-Revell (2019) and Rogerson-Revell (2021), the study examines the pedagogical implications of ASR, its reliability, and its effectiveness. Through a mixed-method approach incorporating experimental data and learner feedback, this research evaluates the impact of ASR-based pronunciation training on learners’ phonetic accuracy, fluency, and confidence. Findings highlight that ASR tools can provide consistent feedback, reduce pronunciation anxiety, and promote self-directed learning, giving learners more independence in their learning journey, though challenges remain regarding recognition errors and accent biases. The study contributes to the ongoing discourse on EdTech in ESL, offering insights into the potential and limitations of speech recognition technology for pronunciation training.