Title |
Efficient Spoken Dialogue Domain Representation and Interpretation |
Authors |
Tobias Heinroth, Dan Denich, Alexander Schmitt and Wolfgang Minker |
Abstract |
We provide a detailed look on the functioning of the OwlSpeak Spoken DialogueManager, which is part of the EU-funded project ATRACO. OwlSpeak interpretsSpoken Dialogue Ontologies and on this basis generates VoiceXML dialoguesnippets. The dialogue snippets can be interpreted by all speech servers thatprovide VoiceXML support and therefore make the dialogue management independentfrom the hosting systems providing speech recognition and synthesis. Ontologiesare used within the framework of our prototype to represent specific spokendialogue domains that can dynamically be broadened or tightened during anongoing dialogue. We provide an exemplary dialogue encoded as OWL model andexplain how this model is interpreted by the dialogue manager. The combinationof a unified model for dialogue domains and the strict model-view-controllerarchitecture that underlies the dialogue manager lead to an efficient systemthat allows for a new way of spoken dialogue system development and can be usedfor further research on adaptive spoken dialogue strategies. |
Language |
Language modelling |
Topics |
Dialogue, Knowledge Discovery/Representation, Language modelling |
Full paper  |
Efficient Spoken Dialogue Domain Representation and Interpretation |
Bibtex |
@InProceedings{HEINROTH10.345,
author = {Tobias Heinroth, Dan Denich, Alexander Schmitt and Wolfgang Minker}, title = {Efficient Spoken Dialogue Domain Representation and Interpretation}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |