A simple multiple-level HMM is presented in which speech dynamics are modelled as linear trajectories in an intermediate, formant-based representation and the mapping between the intermediate and acoustic data is achieved using one or more linear transformations. An upper-bound on the performance of such a system is established. Experimental results on the TIMIT corpus demonstrate that, if the dimension of the intermediate space is sufficiently high or the number of articulatory-to-acoustic mappings is sufficiently large, then this upper-bound can be achieved.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Development of articulatory-based multilevel segmental HMMs for phonetic classification in ASR


    Beteiligte:
    Russell, M.J. (Autor:in) / Jackson, P.J.B. (Autor:in) / Wong, M.L.P. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    317423 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Development of Articulatory-Based Multi-Level Segmental HMMs for Phonetic Classification in ASR

    Russell, M. J. / Jackson, P. J. B. / Wong, M. L. P. et al. | British Library Conference Proceedings | 2003


    Joint class identification and target classification using multiple HMMs

    Xiaofan He, / Tharmarasa, Ratnasingham / Kirubarajan, Thia et al. | IEEE | 2014