Using Automatic Speech Recognition to Enhance Education for All Students: Turning a Vision into Reality

Legislation requires that educational materials produced by staff should be accessible to disabled students. Speech materials therefore require captioning and the Liberated Learning Initiative has demonstrated that automatic speech recognition provides the potential to make teaching accessible to all and to assist learners to manage and search online digital multimedia resources. This could improve the quality of education as the automatic provision of accessible synchronised lecture notes enables students to concentrate on learning and enables teachers to monitor and review what they said and reflect on it to improve their teaching. Standard automatic speech recognition software lacks certain features that are required to make this vision a reality. The only automatic speech recognition tool that is being developed to specifically overcome these identified problems would appear to be IBM ViaScribe and investigation of its application in educational environments is occurring through the Liberating Learning Consortium. This paper will describe both achievements and current developments.