A rule-based backchannel prediction model using pitch and pause information

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

    47 Citations (Scopus)
    185 Downloads (Pure)

    Abstract

    We manually designed rules for a backchannel (BC) prediction model based on pitch and pause information. In short, the model predicts a BC when there is a pause of a certain length that is preceded by a falling or rising pitch. This model was validated against the Dutch IFADV Corpus in a corpus-based evaluation method. The results showed that our model performs slightly better than another well-known rule-based BC prediction model that uses only pitch information. We observed that the length of a pause preceding a BC is one of the important features in this model, next to the duration of the pitch slope at the end of an utterance. Further, we discuss implications of a corpus-based approach to BC prediction evaluation.
    Original languageUndefined
    Title of host publicationProceedings of Interspeech 2010
    PublisherInternational Speech Communication Association
    Pages3058-3061
    Number of pages4
    ISBN (Print)1990-9772
    Publication statusPublished - Sept 2010
    Event11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 - Makuhari, Chiba, Japan
    Duration: 26 Sept 201030 Sept 2010
    Conference number: 11
    http://www.interspeech2010.jpn.org/

    Publication series

    Name
    PublisherInternational Speech Communication Association (ISCA)
    ISSN (Print)1990-9772

    Conference

    Conference11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
    Abbreviated titleINTERSPEECH
    Country/TerritoryJapan
    CityMakuhari, Chiba
    Period26/09/1030/09/10
    Internet address

    Keywords

    • METIS-271083
    • Backchannel prediction
    • HMI-SLT: Speech and Language Technology
    • Prosody
    • EWI-18627
    • IR-74048

    Cite this