The use of spectral transformation to perform speaker adaptation for HMM based speech recognition is investigated. Three estimation methods, namely, minimum mean square error (MMSE), canonical correlation analysis (CCA) and multilayer perceptrons (MLP), for computing the transformation are compared. Using isolated words from the TI-46 database, it is found that CCA has the best adaptation performance. Moreover, a "training-after-adaptation" approach is found to have a higher adaptation performance than the one in which reference HMMs are not re-trained. With a suitable choice of reference speaker, less than 30% of training data from a new speaker is required in order to achieve the same accuracy as the speaker-dependent models of that new speaker, when the CCA method is used with the "training-after-adaptation" approach.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Speaker adaptation through spectral transformation for HMM based speech recognition


    Contributors:
    Choi, H.C. (author) / King, R.W. (author)


    Publication date :

    1994-01-01


    Size :

    324217 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Speaker Adaptation Through Spectral Transformation for HMM Based Speech Recognition

    Choi, H. C. / King, R. W. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994


    Air traffic control speech recognition system cross-task & speaker adaptation

    de Cordoba, R. / Ferreiros, J. / San-Segundo, R. et al. | IEEE | 2006



    Mathematical Analysis and Speaker-Independent Speech Recognition

    Gur'yanov, A. E. | British Library Online Contents | 1996


    Speaker-independent speech recognition based on a fast NN algorithm

    Tian, L. / Lu, X.-s. / Bai, S.-z. | British Library Online Contents | 2002