Digital Signal Processing Reference
In-Depth Information
Our initial prototype system implements much of the architecture
described above. Dialog scenarios are written in ScenarioXML, which
combines the pre-defined dialog structure with dynamic information provided
by the Route Planner in real time. The VoiceXML file includes several turns
of the dialog, and the asynchronous communication channel of the
VoiceXML Interpreter is used to advance the dialog in accordance with the
vehicle's movement.
In the current system, context switching (between multiple active dialog
instances) is realized by a push-and-pop style manipulation of a dialog stack.
We are currently testing an extension of our architecture which uses session
variables to enable switching between multiple (parallel) active dialogs.
ACKNOWLEDGEMENTS
The authors would like to thank Ichiro Akahori and Masahiko Tateishi of
DENSO Research Laboratories for their support in collecting dialog corpora
and assisting in the design and development of the initial prototype system.
REFERENCES
W3C, “Voice Extensible Markup Language (VoiceXML) Version 2.0 Working Draft,”
http://www.w3c.org/TR/voicexml20/
B. Carpenter, S. Caskey, K. Dayanidhi, C. Drouin, and R. Pieraccini, “A Portable, Server-
Side Dialog Framework for VoiceXML,” Proc. of International Conference on Spoken
Language Processing, 2002
R. Pieraccini, S. Caskey, K. Dayanidhi, B. Carpenter, and M. Phillips, “ETUDE: A
Recursive Dialog Manager with Embedded User Interface Patterns,” Proc. of IEEE
Workshop on Automatic Speech Recognition and Understanding, 2001
E. Nyberg, T. Mitamura, P. Placeway, and M. Duggan, “DialogXML: Extending
VoiceXML for dynamic dialog management,” Proc. of Human Language Technology
Conference, 2002
Sun Microsystems, “JavaServer Pages,” http://java.sun.com/products/jsp/
X. Huang, F. Alleva, H. Hon, M. Hwang, K. Lee, and R. Rosenfeld, “The SPHINX-II
Speech Recognition System: An Overview,” Computer Speech and Language,” vol.2,
pp.137-148, 1993
E. Nyberg, and T. Mitamura, “The KANTOO Machine Translation Environment,” Proc.
of AMTA-2000
T. Kujirai, H. Takahashi, A. Amano, and N. Hataoka, “Development of VoiceXML
Interpreter and Continuous Words Recognition Engine - Development of Speech
Recognition Technologies for Voice Portal,” (in Japanese) IPSJ SIGNotes, SLP-33-12,
2000
M. Tateishi, I. Akahori, S. Judy, Y. Obuchi, T. Mitamura, and E. Nyberg, “A Spoken
Dialog Corpus for Car Telematics Services,” Proc. of Workshop on DSP in Vehicular and
Mobile Systems, 2003
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9]
