Investigating applications of speech-to-text recognition technology for a face-to-face seminar to assist learning of non-native English-speaking participants

Rustam Shadiev, Wu Yuin Hwang, Yueh-Min Huang, Chia Ju Liu

Research output: Contribution to journalArticle

23 Citations (Scopus)


This study applied speech-to-text recognition (STR) technology to assist non-native English-speaking participants to learn at a seminar given in English. How participants used transcripts generated by the STR technology for learning and their perceptions toward the STR were explored. Three main findings are presented in this study. Most participants perceived that transcripts were useful for learning. Nineteen learning strategies to use transcripts were discovered; transcripts were used to understand the topic presented, to find an answer to a question and to write summaries. Participants with different learning achievements demonstrated different learning behaviours when using transcripts. That is, some participants used transcripts effectively (i.e. studied them thoroughly and used the most important parts of them for summaries along with elaborating ideas) but some participants did not (i.e. studied transcripts superficially and employed the copy-and-paste method to complete summaries). Therefore, this study suggests how to teach participants to use transcripts by employing learning strategies meaningfully.

Original languageEnglish
Pages (from-to)119-134
Number of pages16
JournalTechnology, Pedagogy and Education
Issue number1
Publication statusPublished - 2016 Jan 1


All Science Journal Classification (ASJC) codes

  • Information Systems
  • Education
  • Communication
  • Computer Science Applications

Cite this