A Composite Framework for Affective Sensing

Gordon McIntyre, Roland Goecke

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    A system capable of interpreting affect from a speaking face
    must recognise and fuse signals from multiple cues. Building
    such a system requires the integration of software components
    to perform tasks such as image registration, video segmentation, speech recognition and classification. Such software components tend to be idiosyncratic, purpose-built, and driven by
    scripts and textual configuration files. Integrating components
    to achieve the necessary degree of flexibility to perform full
    multimodal affective recognition is challenging. We discuss the
    key requirements and describe a system to perform multimodal
    affect sensing which integrates such software components and
    meets these requirements.
    Original languageEnglish
    Title of host publicationInvalid Code
    Place of PublicationGermany
    PublisherSpringer
    Pages104-115
    Number of pages12
    Volume4868
    ISBN (Print)0302-9743
    Publication statusPublished - 2008
    Event9th Annual Conference of the International Speech Communication Association - Brisbane, Australia
    Duration: 22 Sep 200826 Sep 2008

    Conference

    Conference9th Annual Conference of the International Speech Communication Association
    CountryAustralia
    CityBrisbane
    Period22/09/0826/09/08

    Fingerprint

    Image registration
    Electric fuses
    Speech recognition
    Composite materials

    Cite this

    McIntyre, G., & Goecke, R. (2008). A Composite Framework for Affective Sensing. In Invalid Code (Vol. 4868, pp. 104-115). Germany: Springer.
    McIntyre, Gordon ; Goecke, Roland. / A Composite Framework for Affective Sensing. Invalid Code. Vol. 4868 Germany : Springer, 2008. pp. 104-115
    @inproceedings{ec811cfb602943a694230adac5bffb7e,
    title = "A Composite Framework for Affective Sensing",
    abstract = "A system capable of interpreting affect from a speaking facemust recognise and fuse signals from multiple cues. Buildingsuch a system requires the integration of software componentsto perform tasks such as image registration, video segmentation, speech recognition and classification. Such software components tend to be idiosyncratic, purpose-built, and driven byscripts and textual configuration files. Integrating componentsto achieve the necessary degree of flexibility to perform fullmultimodal affective recognition is challenging. We discuss thekey requirements and describe a system to perform multimodalaffect sensing which integrates such software components andmeets these requirements.",
    author = "Gordon McIntyre and Roland Goecke",
    year = "2008",
    language = "English",
    isbn = "0302-9743",
    volume = "4868",
    pages = "104--115",
    booktitle = "Invalid Code",
    publisher = "Springer",
    address = "Netherlands",

    }

    McIntyre, G & Goecke, R 2008, A Composite Framework for Affective Sensing. in Invalid Code. vol. 4868, Springer, Germany, pp. 104-115, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, 22/09/08.

    A Composite Framework for Affective Sensing. / McIntyre, Gordon; Goecke, Roland.

    Invalid Code. Vol. 4868 Germany : Springer, 2008. p. 104-115.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - A Composite Framework for Affective Sensing

    AU - McIntyre, Gordon

    AU - Goecke, Roland

    PY - 2008

    Y1 - 2008

    N2 - A system capable of interpreting affect from a speaking facemust recognise and fuse signals from multiple cues. Buildingsuch a system requires the integration of software componentsto perform tasks such as image registration, video segmentation, speech recognition and classification. Such software components tend to be idiosyncratic, purpose-built, and driven byscripts and textual configuration files. Integrating componentsto achieve the necessary degree of flexibility to perform fullmultimodal affective recognition is challenging. We discuss thekey requirements and describe a system to perform multimodalaffect sensing which integrates such software components andmeets these requirements.

    AB - A system capable of interpreting affect from a speaking facemust recognise and fuse signals from multiple cues. Buildingsuch a system requires the integration of software componentsto perform tasks such as image registration, video segmentation, speech recognition and classification. Such software components tend to be idiosyncratic, purpose-built, and driven byscripts and textual configuration files. Integrating componentsto achieve the necessary degree of flexibility to perform fullmultimodal affective recognition is challenging. We discuss thekey requirements and describe a system to perform multimodalaffect sensing which integrates such software components andmeets these requirements.

    M3 - Conference contribution

    SN - 0302-9743

    VL - 4868

    SP - 104

    EP - 115

    BT - Invalid Code

    PB - Springer

    CY - Germany

    ER -

    McIntyre G, Goecke R. A Composite Framework for Affective Sensing. In Invalid Code. Vol. 4868. Germany: Springer. 2008. p. 104-115