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

Background While automatic speech recognition (ASR) is increasingly used for commercial purposes, its influence on the learners' linguistic performance in terms of oral complexity, accuracy and fluency was under-explored. To date, few studies have been conducted to investigate how the dictation ASR technology could be incorporated into language classrooms to facilitate the learners' language acquisition. Objectives This study aimed to examine the effects of ASR-based technology on English learners' oral accuracy and fluency and depict the corresponding development trajectories. Methods A total of 160 first-year university students were enrolled in a 14-week quasi-experiment based on a longitudinal research design. Both treatment and control groups were taught with the flipped classroom approach, but the students in the treatment group were particularly required to undertake a pre-class task with ASR technology. Students' Unit Task performance was audio-recorded, and the metrics of oral accuracy and fluency were coded and computed based on the recording transcripts. A two-way repeated measures ANCOVA was conducted to investigate the between- and within-subjects effects as well as the corresponding interaction effects. Results In terms of the between-subjects effect, the treatment group outperformed the control group on phonological accuracy, speed fluency and repair fluency. In terms of the within-subjects effect, significant gains in lexical and morphosyntactic accuracy were witnessed over time in both groups, but the performance of the treatment group tended to be more stable. On all the fluency metrics and phonological accuracy, no significant within-subjects improvement was seen over time. Implications The development of oral accuracy may generate a negative impact on that of fluency. Therefore, course developers and teachers need to design special tasks and provide conditions conducive to the development of the students' oral fluency. Moreover, the mobile-based dictation ASR application could incorporate adaptive artificial intelligence, which may escalate the students' fossilization of learner interlanguage.