We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likelihoods of (a) HMM used to model phonemes from the acoustic signal, and (b) HMM used to model visual features motions from video. One significant addition is the dynamic analysis with features selected by AdaBoost, on the basis of their discriminant ability. This form of integration, leading to boosted HMM, permits AdaBoost to find the best features first, and then uses HMM to exploit dynamic information inherent in the signal.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Boosted audio-visual HMM for speech reading


    Beteiligte:
    Pei Yin, (Autor:in) / Essa, I. (Autor:in) / Rehg, J.M. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    289856 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Boosted Audio-Visual HMM for Speech Reading

    Yin, P. / Essa, I. / Rehg, J. et al. | British Library Conference Proceedings | 2003


    Asymmetrically Boosted HMM for Speech Reading

    Yin, P. / Essa, I. / Rehg, J. et al. | British Library Conference Proceedings | 2004


    Asymmetrically boosted HMM for speech reading

    Pei Yin, / Essa, I. / Rehg, J.M. | IEEE | 2004


    Audio-Visual Speech Recognition using SciPy

    Reikeras, Helge / Herbst, Ben / Preez, Johan du et al. | TIBKAT | 2010


    Measuring Audio and Visual Speech Synchrony: Methods and Applications

    Bredin, H. / Chollet, G. / Visual Information Engineering Network (Institution of Engineering and Technology) | British Library Conference Proceedings | 2006