An exploration of the potential of Automatic Speech Recognition to assist and enable receptive communication in higher education

Abstract

The potential use of Automatic Speech Recognition to assist receptive communication is explored. The opportunities and challenges that this technology presents students and staff to provide captioning of speech online or in classrooms for deaf or hard of hearing students and assist blind, visually impaired or dyslexic learners to read and search learning material more readily by augmenting synthetic speech with natural recorded real speech is also discussed and evaluated. The automatic provision of online lecture notes, synchronised with speech, enables staff and students to focus on learning and teaching issues, while also benefiting learners unable to attend the lecture or who find it difficult or impossible to take notes at the same time as listening, watching and thinking.

Towards Universally Designed Communication: Opportunities and Challenges in the Use of Automatic Speech Recognition Systems to Support Access, Understanding and Use of Information in Communicative Settings

“…Researchers have been investigating how diverse populations may use ASR outputs in various settings. For example, in educational settings, students may use transcriptions to support note-taking and revision of previous notes [1,9,[19][20][21][22]. Regarding real-time captioning, researchers have investigated how captions affect comprehension during work meetings where communication is carried out in a foreign language (English in the majority of cases).…”

“…In the educational setting, for example, research on the benefits of captions on language comprehension in different populations, has mainly focused on human-made subtitles, while ASRgenerated captions have generally received less attention. ASR has been the core of the Liberated Learning concept, a project that focuses on how these systems could "provide universal access to lecture material for students with diverse backgrounds" [1,[19][20][21][22]. Experimental studies conducted in this project and others have highlighted the benefits for students (e.g., an increase in word recognition and better comprehension of the content of lectures), but they have also sought to surface common problems with current ASR systems.…”

“…Experimental studies conducted in this project and others have highlighted the benefits for students (e.g., an increase in word recognition and better comprehension of the content of lectures), but they have also sought to surface common problems with current ASR systems. The major problem (as already briefly mentioned) was the lack of accuracy in transcriptions [1,9,[19][20][21][22].…”

“…Developers are facing many challenges to improving ASR [24,25], and some of the problems are currently undermining the implementation of these systems as a primary service in various settings [9]. Feedback from users also highlights the need to increase transcription accuracy before considering the adoption of this technology to support communication and facilitate access to information in universally designed environments [1,9,20,21].…”

Using podcasts to support learners` positive attitude to listening comprehension in TEFL

“…Podcasts, as many other Internet resources have also some disadvantages. Wald (2006) points out that downloaded podcasts can create difficulties, for example to identify an accurate phrase within a podcast. If learners want to find it, the only way to reach it would be repeated listening to the section of the podcast.…”