Analyzing Effect of Repeated Reading on Oral Fluency and Narrative Production for Computer-Assisted Language Learning
This work provides a dataset and assessment method for language learners and educators, though it is incremental as it applies existing techniques to a new domain.
The researchers addressed the lack of open audio datasets for analyzing repeated reading practices in language learning by creating a new dataset and proposing a method to assess oral fluency and narrative production using acoustic, prosodic, lexical, and syntactical features. Their results demonstrate that a computer-assisted language learning system can effectively evaluate improvements in learners' oral fluency and narrative production.
Repeated reading (RR) helps learners, who have little to no experience with reading fluently to gain confidence, speed and process words automatically. The benefits of repeated readings include helping all learners with fact recall, aiding identification of learners' main ideas and vocabulary, increasing comprehension, leading to faster reading as well as increasing word recognition accuracy, and assisting struggling learners as they transition from word-by-word reading to more meaningful phrasing. Thus, RR ultimately helps in improvements of learners' oral fluency and narrative production. However, there are no open audio datasets available on oral responses of learners based on their RR practices. Therefore, in this paper, we present our dataset, discuss its properties, and propose a method to assess oral fluency and narrative production for learners of English using acoustic, prosodic, lexical and syntactical characteristics. The results show that a CALL system can be developed for assessing the improvements in learners' oral fluency and narrative production.