Abstract:

The post-secondary educational environment can be extremely challenging for students with disabilities, those studying in second language environments, and other at risk populations. A key challenge facing these stakeholders is access to lecture content and the requirement for adequate notetaking skills. To meet these needs, instructors and institutions require both creative pedagogy and universally designed teaching/learning technologies.

This presentation reviews the use of speech recognition to automatically caption and transcribe course media, including live presentations and eLearning content. In various international universities and colleges, instructors are using speech recognition to create “multimedia transcripts” that can be used by a variety of at risk learners to improve access to information. Students with various disabilities can also benefit from the provision of speech recognition generated captions during live presentations. These emerging technologies may be used to augment traditional support services available to students with disabilities, including the provision of notetaking.

This presentation will review various case studies from institutions in the European Union, North America, and Australia. Topics include a review of research outcomes, available speech recognition prototypes, and technological and pedagogical challenges. The session will also highlight the benefits and challenges of international collaboration between universities and industry partners.

Keywords:

Accessibility, lecture transcription, speech recognition, multimedia.