Effects of Automatic Speech Recognition Software on Pronunciation for Adults With Different Learning Styles

Abstract

This study investigated how learning styles (visual/verbal) and the use of Automatic Speech Recognition (ASR) software affect English as a Second Language adult learners’ improvement during a 12-week course focusing on pronunciation. In the control group (n = 28), the teacher corrected and gave feedback on the adult learners’ pronunciation; experimental group 1 (n = 33) used dictation ASR along with peers’ correction; and experimental group 2 (n = 31) used dictation ASR alone. Their pre- and post-tests on pronunciation in reading tasks and live conversation were analyzed with their learning styles taken into account, using 2-way ANCOVA. The results suggest that learning styles made a significant difference in the pronunciation performance of the reading task in all groups. Visual style learners outperformed verbal style learners in the reading task. The combination of ASR and peer correction yielded the highest improvement in both reading tasks and live conversation.

Exploring the effects of automatic speech recognition technology on oral accuracy and fluency in a flipped classroom

“…McCrocklin (2016) assessed changes in the students' stated beliefs of autonomy and autonomous learning behaviours using self‐reported questionnaires, learning logs and interviews. Evers and Chen (2020, 2021) surveyed adult EFL learners' learning styles via questionnaires and used human rating method to evaluate the effects of an ASR system on the students' pronunciation performance. Although they are widely used in studies, student self‐reported data are subjective and tend to be biased to some extent (Wilson & Zietz, 2004).…”

“…In view of the pedagogical and technological design, the previous studies mainly adopted ASR‐based CAPT for FL pronunciation learning and the use of mobile‐based dictation ASR was largely overlooked in FL instruction (Evers & Chen, 2021). Since they are designed for native speakers and can work for natural language use, dictation ASR programs can be used for higher order speaking practice to help FL learners monitor their utterances.…”

“…Automatic speech recognition (ASR) technology has gradually attracted the attention of researchers and practitioners in foreign language (FL) education and a growing number of studies have been carried out to investigate its special effects on the learners' oral performance in the target language (e.g. Evers & Chen, 2020, 2021; Franco et al, 2010; Jiang, Jong, Wu, et al, 2022; van Doremalen et al, 2016). Apart from various ASR‐based commercial systems available such as Duolingo and iFlyRec, some academic ASR‐based language learning programs have been developed in educational institutions (e.g.…”

“…Although the reliance on language teachers to provide feedback is not considered unreasonable, it is quite impossible for FL teachers to provide timely and sufficient feedback on an individual basis. Owing to the advancement of educational technology, ASR technology is progressively regarded as a conceivable solution to address this issue in FL learning (Bashori et al, 2021; De Vries et al, 2015; Evers & Chen, 2021; Mroz, 2018). Accordingly, it is of pedagogical significance that FL researchers further the understanding of how ASR may benefit FL learners' oracy development.…”

An Empirical Performance Analysis of the Speak Correct Computerized Interface

“…Evers and Chen [17] evaluated how learning methods (visual/verbal), including how the use of ASR software impacts adult learners, improved performance in English as a second language throughout a 12 week curriculum concentrating on pronunciation. According to the findings, the learning strategies produced a large disparity in the pronunciation effectiveness of the reading process across all teams.…”