The idea of using speech recognition in Computer-Assisted Language Learning is becoming increasingly popular. Early systems focussed on pronunciation practice; applications are now emerging designed to carry out simple conversations with students and give them the opportunity to practise spontaneous speaking skills. Despite positive anecdotal studies, it still remains to be demonstrated that conversation with a mechanical partner is in fact able to help students acquire language skills, and, if so, which features influence learning outcomes. The current project is aimed at systematic investigation of the issues involved.
Our starting point is the CALL-SLT system, built under an earlier SNF-funded project. During the first half of the project, we will extend the existing prototype, in particular improving speech recognition and recognition feedback strategies, developing a substantial quantity of new English and French course content, and embedding the system inside a social network. In the second half, we will use these resources to carry out a series of substantial evaluations in secondary schools, universiities and on the web.