Lecture Instrumentation Based on Synchronous Speech Transcription

Abstract

Speech transcription can now be achieved quickly enough to generate subtitles in real-time. Research presented in this paper aims to explore the potential of synchronous transcription in instrumenting learning environments, specifically in the context of hybrid lectures. Considering available technologies, we designed a toolset in order to answer the existing needs of students and teachers. This toolset is built around the transcription of the teacher's speech, which acts as a support for interactions and provides data needed by other functionalities. We present here the different interfaces and their components, as well as the results of the user test carried out in real life conditions.