SLaTE 2015 - Workshop on Speech and Language Technology in Education
We summarise experiments carried out using a system-initiative spoken CALL system, in which permitted responses to prompts are defined using a minimal formalism based on templates and regular expressions, and describe a simple structural learning algorithm that uses annotated data to update response definitions. Using 1 927 utterances of training data, we obtained a relative improvement of 20% in the systems ability to react differentially to correct and incorrect input, measured on a previously unseen test set. The results are significant at p < 0.005.
Bibliographic reference. Rayner, Manny / Baur, Claudia / Chua, Cathy / Tsourakis, Nikos (2015): "Supervised learning of response grammars in a spoken call system", In SLaTE-2015, 83-88.