Human speech is inherently multi-modal, consisting of both audio and visual components. Recently researchers have shown that the incorporation of information about the position of the lips into acoustic speech recognisers enables robust recognition of noisy speech. In the case of Hidden Markov Model-recognition, we show that this happens because the visual signal stabilises the alignment of states. It is also shown, that unadorned lips, both the inner and outer contours, can be robustly tracked in real time on general-purpose workstations. To accomplish this, efficient algorithms are employed which contain three key components: shape models, motion models, and focused colour feature detectors-all of which are learnt from examples.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Accurate, real-time, unadorned lip tracking


    Beteiligte:
    Kaucic, R. (Autor:in) / Blake, A. (Autor:in)


    Erscheinungsdatum :

    01.01.1998


    Format / Umfang :

    792676 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Accurate, Real-Time, Unadorned Lip Tracking

    Kaucic, R. / Blake, A. / IEEE; Computer Society | British Library Conference Proceedings | 1998



    Real-time target tracking

    Baumela, L. / Maravall, D. | IEEE | 1995


    Real-Time Target Tracking

    Baumela | Online Contents | 1995


    REAL-TIME VESSEL NAVIGATION TRACKING

    MOORE DAVID MARTIN / OTTERLEE MARK ALEXANDER / DUNAGAN PATRICK et al. | Europäisches Patentamt | 2021

    Freier Zugriff