A Multi-lingual Evaluation of the vAssist Spoken Dialog System. Comparing Disco and RavenClaw

Javier Mikel Olaso, Pierrick Milhorat, Julia Himmelsbach, Jerome Boudy, Gerard Chollet, Stephan Schlögl, Maria Ines Torres (Vortragende:r)

Publikation: Beitrag in Buch oder TagungsbandVortrag mit Beitrag in TagungsbandBegutachtung

Abstract

vAssist (Voice Controlled Assistive Care and Communication Services for the Home) is a European project for which several research institutes and companies have been working on the development of adapted spoken interfaces to support home care and communication services. This paper describes the spoken dialog system that has been built. Its natural language understanding module includes a novel reference resolver and it introduces a new hierarchical paradigm to model dialog tasks. The user-centered Approach applied to the whole development process led to the setup of several experiment sessions with real users. Multilingual experiments carried out in Austria, France and Spain are described along with the analyses and results in terms of both system performance and user experience. An additional experimental comparison of the RavenClaw and Disco-LFF dialog Managers built into the vAssist spoken dialog system highlighted similar Performance and user acceptance.
OriginalspracheEnglisch
TitelDialogues with Social Robots. Enablements, Analyses, and Evaluation
Redakteure/-innenKristiina Jokinen, Graham Wilcock
Herausgeber (Verlag)Springer Singapore
Seiten221-232
Seitenumfang12
ISBN (Print)978-981-10-2585-3
DOIs
PublikationsstatusVeröffentlicht - 2017
VeranstaltungIWSDS 2016 : The Seventh International Workshop on Spoken Dialogue Systems -
Dauer: 13 Jan. 201616 Jan. 2016

Konferenz

KonferenzIWSDS 2016 : The Seventh International Workshop on Spoken Dialogue Systems
Zeitraum13/01/1616/01/16

Research Field

  • Nicht definiert

Schlagwörter

  • spoken dialog systems
  • dialog management
  • real-user experiments

Fingerprint

Untersuchen Sie die Forschungsthemen von „A Multi-lingual Evaluation of the vAssist Spoken Dialog System. Comparing Disco and RavenClaw“. Zusammen bilden sie einen einzigartigen Fingerprint.

Diese Publikation zitieren