Key points are not available for this paper at this time.
This article provides an overview and evaluation of the uses—actual and potential—of automatic speech recognition (ASR) and spoken dialogue systems (SDS), related technologies that can be applied to second language speaking assessment, given particular definitions of the construct. Both technologies have only gradually moved in the direction of supporting language learning, and only more recently used for grading purposes. How the speaking construct is defined determines one’s evaluation of the extent to which assessments using these technologies are adequate to the task, given different test use contexts, and what the challenges and future research requirements are. In any event there are many opportunities for their use in assessment, and these would be facilitated by increased cross-disciplinary research among the language testing and speech technology communities.
Litman et al. (Mon,) studied this question.