UNIGE document Chapitre d'actes
previous document  unige:73662  next document
add to browser collection
Title

Supervised Learning of Response Grammars in a Spoken Call System

Authors
Chua, Cathy
Published in Workshop on Speech and Language Technology in Education (SLaTE) - Leipzig (Germany) - . 2015
Abstract 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 system’s ability to react differentially to correct and incorrect input, measured on a previously unseen test set. The results are significant at p < 0:005.
Full text
Structures
Citation
(ISO format)
RAYNER, Emmanuel et al. Supervised Learning of Response Grammars in a Spoken Call System. In: Workshop on Speech and Language Technology in Education (SLaTE). [s.l.] : [s.n.], 2015. https://archive-ouverte.unige.ch/unige:73662

239 hits

49 downloads

Update

Deposited on : 2015-06-24

Export document
Format :
Citation style :