Multimodal Access Enabler Based on Adaptive Keyword Spotting (original) (raw)

Abstract

The Multimodal Access Enabler is a Service Layer HTTP/Speech Proxy, which extracts keywords from HTML/XHTML pages given a set of predefined rules. The keywords are highlighted, in this way providing an indication to the user on which words to use in speech commands, when selecting a specific hyperlink. Synchronisation of the HTTP User Agent and the Speech Agent, is achieved using a “Push” module located in the HTTP/Speech Proxy. This module triggers page reload command execution in MS User Agent, once the page requested by voice command has been fetched. For unrecognised voice commands, the Multimodal Access Enabler uses a TTS module to synthesise speech dialogs/prompts, which either ask the user to select a command from a given set, and/or to repeat his command.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bodell, M., Johnston, M., Kumar, S., Potter, S., Waters, K.: W3C Multimodal Interaction Framework. World Wide Web Consortium (2003)
    Google Scholar
  2. McGlashan, S., Burnett, D.C., Carter, J., Danielsen, P., Ferrans, J., Hunt, A., Lucas, B., Porter, B., Rehor, K., Tryphonas, S. (eds.): Voice Extensible Markup Language (VoiceXML) Version 2.0. World Wide Web Consortium (2004)
    Google Scholar
  3. SALT Forum Companies (eds.): SALT Speech Application Language Tags (SALT) 1.0 Specification. SALT Forum (2002)
    Google Scholar
  4. WAP Forum Companies (eds.): Wireless Markup Language Version 2.0. WAP Forum (2001)
    Google Scholar
  5. WAP Forum Companies (eds.): WMLScript Standard Libraries Specification. WAP Forum (2001)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Ericsson Research Canada, System Management, 8500 Decarie Blvd, H4P2N2, Montreal, Canada
    Sorin-Marian Georgescu

Authors

  1. Sorin-Marian Georgescu

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of Beira Interior, Rua Marques d’Avila e Bolama, 6201-001, Covilha, Portugal
    Mário Marques Freire
  2. France Telecom, Research and Development, CORE/SPP, 37-40 rue du Général Leclerc, 92794, Issy-les-Moulineaux Cedex 9, France
    Prosper Chemouil
  3. IUT, University of Haute Alsace, 34, rue du Grillenbreit, 68008, Colmar, France
    Pascal Lorenz
  4. Département Informatique, ENST-Bretagne, CS 83818, 29238, Brest Cedex 3, France
    Annie Gravey

Rights and permissions

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Georgescu, SM. (2004). Multimodal Access Enabler Based on Adaptive Keyword Spotting. In: Freire, M.M., Chemouil, P., Lorenz, P., Gravey, A. (eds) Universal Multiservice Networks. ECUMN 2004. Lecture Notes in Computer Science, vol 3262. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30197-4\_35

Download citation

Keywords

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Publish with us