Toward a Model for Incremental Grounding in Spoken Dialogue Systems

Thomas Visser, David Traum, David DeVault, Rieks op den Akker

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    86 Downloads (Pure)


    Recent advances in incremental language processing for dialogue systems promise to enable more natural conversation between humans and computers. By analyzing the user's utterance while it is still in progress, systems can provide more human-like overlapping and backchannel responses to convey their level of understanding and respond more quickly. In this paper, we look at examples of several overlapping response types in human-human dialogues, and present an initial computational model of the incremental grounding process in these responses. Additionally, we describe an implementation of this model in a virtual human dialogue system that can provide backchannels, head nods, frowns, completions and low latency responses.
    Original languageEnglish
    Title of host publicationJoint Proceedings of the Intelligent Virtual Agents 2012 Workshops
    Subtitle of host publicationSanta Cruz, California, September 15, 2012
    EditorsRonald Böck, Francesca Bonin, Nick Campbell, Jens Edlund, Iwan de Kok, Ronald Poppe, David Traum
    Place of PublicationMagdeburg, Germany
    PublisherOtto von Guericke University Magdeburg
    Number of pages8
    ISBN (Print)978-3-940961-83-9
    Publication statusPublished - 15 Sept 2012
    EventWorkshop on Real-Time Conversations with Virtual Agents, RCVA 2012 - Santa Cruz, United States
    Duration: 15 Sept 201215 Sept 2012


    WorkshopWorkshop on Real-Time Conversations with Virtual Agents, RCVA 2012
    Abbreviated titleRCVA
    Country/TerritoryUnited States
    CitySanta Cruz


    • HMI-HF: Human Factors
    • Spoken dialogue systems
    • Grounding
    • Incremental language processing


    Dive into the research topics of 'Toward a Model for Incremental Grounding in Spoken Dialogue Systems'. Together they form a unique fingerprint.

    Cite this