Using speech recognition for real-time captioning and lecture transcription in the classroom

Abstract

Speech recognition (SR) technologies were evaluated in different classroom environments to assist students to automatically convert oral lectures into text. Two distinct methods of SR-mediated lecture acquisition (SR-mLA), real-time captioning (RTC) and postlecture transcription (PLT), were evaluated in situ life and social sciences lecture courses employing typical classroom equipment. Both methods were compared according to technical feasibility and reliability of classroom implementation, instructors' experiences, word recognition accuracy, and student class performance. RTC provided near-instantaneous display of the instructor's speech for students during class. PLT employed a user-independent SR algorithm to optimally generate multimedia class notes with synchronized lecture transcripts, instructor audio, and class PowerPoint slides for students to access online after class. PLT resulted in greater word recognition accuracy than RTC. During a science course, students were more likely to take optional online quizzes and received higher quiz scores with PLT than when multimedia class notes were unavailable. Overall class grades were also higher when multimedia class notes were available. The potential benefits of SR-mLA for students who have difficulty taking notes accurately and independently were discussed, particularly for nonnative English speakers and students with disabilities. Field-tested best practices for optimizing SR accuracy for both SR-mLA methods were outlined.

A study of the facilitation of cross‐cultural understanding and intercultural sensitivity using speech‐enabled language translation technology

“…Speech-to-text recognition and computer-aided-translation Scholars suggest that STR technology is a useful tool to aid the learning of students in both physical (Ranchal et al, 2013) and cyber classrooms in the case of both non-native speakers (Shadiev, Wu, & Huang, 2018) and students with cognitive or physical disabilities (Kheir & Way, 2006). For example, students can focus on the lecture instead of taking class notes when lecture transcriptions are available in a physical classroom (Ranchal et al, 2013). In a cyber classroom, students can follow the lecturer by reading STR-texts when network connections are not stable, and they cannot hear the lecturer Kuo et al, 2012).…”

Automated generation of ‘good enough’ transcripts as a first step to transcription of audio-recorded data

“…The searchable nature of transcripts was frequently given as a key benefit over direct coding onto the audio file. Ranchal et al (2013) have studied the use of ASR tools in the context of lecture capture. In their study, they measured the accuracy of the ASR technologies using word error rate and recognition accuracy tools.…”

Lecture Instrumentation Based on Synchronous Speech Transcription

“…Speech transcription allows human actors to access the textual version of a sentence a few seconds after it was said, and browse the whole text as they wish. This tool can help students solving comprehension problems caused by hearing [5], or allow them to use down time to read again a more complex section. Having access to the recording of a lecture decreases students' stress: they express trust in these recordings, which leads them to take fewer notes and concentrate on the teacher's explanations [4].…”