Open AccessComparing the impact of automatically generated and corrected subtitles on cognitive load and learning in a first- and second-language educational context
Author(s) -
Wing Lai Chan,
JanLouis Kruger,
Stephen Doherty
Publication year - 2020
Publication title -
linguistica antverpiensia new series - themes in translation studies
Language(s) - English
Resource type - Journals
ISSN - 2295-5739
DOI - 10.52034/lanstts.v18i0.506
Subject(s) - computer science , presentation (obstetrics) , context (archaeology) , segmentation , natural language processing , software , scalability , multimedia , speech recognition , channel (broadcasting) , mode (computer interface) , artificial intelligence , human–computer interaction , medicine , paleontology , radiology , database , biology , programming language , computer network
The addition of subtitles to videos has the potential to benefit students across the globe in a context where online video lectures have become a major channel for learning, particularly because, for many, language poses a barrier to learning. Automated subtitling, created with the use of speech-recognition software, may be a powerful way to make this a scalable and affordable solution. However, in the absence of thorough post-editing by human subtitlers, this mode of subtitling often results in serious errors that arise from problems with speech recognition, accuracy, segmentation and presentation speed. This study therefore aims to investigate the impact of automated subtitling on student learning in a sample of English first- and second-language speakers. Our results show that high error rates and high presentation speeds reduce the potential benefit of subtitles. These findings provide an important foundation for future studies on the use of subtitles in education.