Evaluation of spoken language systems: the ATIS domain
HLT '90 Proceedings of the workshop on Speech and Natural Language
Mixed-initiative interaction = mixed computation
PEPM '02 Proceedings of the 2002 ACM SIGPLAN workshop on Partial evaluation and semantics-based program manipulation
Talk'n'travel: a conversational system for air travel planning
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Development of the HRL route navigation dialogue system
HLT '01 Proceedings of the first international conference on Human language technology research
Realising voice dialogue management in a collaborative virtual environment
International Journal of Computer Applications in Technology
Compositional specification and realisation of mixed-initiative web dialogs
International Journal of Web Engineering and Technology
Reengineering a domain-independent framework for spoken dialogue systems
SETQA-NLP '08 Software Engineering, Testing, and Quality Assurance for Natural Language Processing
Bus information system based on user models and dynamic generation of VoiceXML scripts
JSAI'03/JSAI04 Proceedings of the 2003 and 2004 international conference on New frontiers in artificial intelligence
Proceedings of the 7th International Conference on Network and Services Management
Hi-index | 0.00 |
The characteristics of VoiceXML make it an attractive choice for the implementation of embedded dialog systems on networked hardware. Nevertheless, VoiceXML lacks some important features found in existing proprietary approaches. It is difficult to build a complex, multi-dialog system directly in VoiceXML. This paper describes DialogXML, an extension to VoiceXML that supports a more implicitly declarative language for dialog scenarios, and ScenarioXML, a straightforward combination of DialogXML with the template-filling mechanism of Java Server Pages. The paper describes an initial prototype system, which extends the OpenVXI VoiceXML interpreter for DialogXML, implements a web server for ScenarioXML, and utilizes the KANTOO natural language analyzer for understanding user inputs.