A novel use of VXML to construct a speech browser for a public-domain speechweb

Authors:
L. Su;R. A. Frost
Affiliations:
School of Computer Science, University of Windsor, Windsor, Ontario, Canada;School of Computer Science, University of Windsor, Windsor, Ontario, Canada
Venue:
AI'05 Proceedings of the 18th Canadian Society conference on Advances in Artificial Intelligence
Year:
2005

Citing 5
Cited 1

Surfing the Web by voice

Proceedings of the third ACM international conference on Multimedia
VoiceXML for Web-based distributed conversational applications

Communications of the ACM
Spoken dialogue technology: enabling the conversational user interface

ACM Computing Surveys (CSUR)
LRRP Speech Webs

CNSR '04 Proceedings of the Second Annual Conference on Communication Networks and Services Research
Call for a public-domain SpeechWeb

Communications of the ACM

Call for a public-domain SpeechWeb

Communications of the ACM

Quantified Score

Hi-index	0.02

Visualization

Abstract

Despite the fact that interpreters for the voice-application markup language VXML have been available for around five years, there is very little evidence of the emergence of a public domain SpeechWeb This is in contrast to the huge growth of the conventional web only a few years after the introduction of HTML One reason for this is that architectures for distributed speech applications are not conducive to public involvement in the creation and deployment of speech applications In earlier work, a new architecture for a public domain SpeechWeb has been proposed In this paper, it is shown how a speech browser for this new architecture can be readily built through a novel use of VXML A detailed description of the browser is given, together with a discussion of the advantages of this novel approach.