The modifications and improvements of the acoustic recognition component of the SPICOS system for the DARPA naval resource management task are described. These modifications and improvements include: the modeling of the continuous mixture densities of the acoustic vectors, the choice of suitable context-dependent phoneme units and the construction of generalized context phoneme units, and the modeling of transitional information in the acoustic vector. The experimental results show that critical factors are the acoustic resolution of the probability distributions and the context information captured in the acoustic vectors. By these enhancements, the system was able to attain a word error rate of 23.6% and 26.5% on two test sets in speaker-independent recognition mode, when trained on 80 speakers. The word pair grammar reduced the word error rate to 7.1% and 9.3% respectively.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Experiments on mixture-density phoneme-modelling for the speaker-independent 1000-word speech recognition DARPA task


    Additional title:

    Experimente für eine Ansatz-verteilte Lautmodellierung für die Sprecher-unabhängige 1000-Wort Spracherkennung DARP


    Contributors:
    Ney, H. (author)


    Publication date :

    1990


    Size :

    4 Seiten, 9 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Mathematical Analysis and Speaker-Independent Speech Recognition

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


    The DARPA PerceptOR evaluation experiments

    Krotkov, E. / Fish, S. / Jackel, L. et al. | British Library Online Contents | 2007


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

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


    Speaker-independent speech recognition based on a fast NN algorithm

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