The recognition process comprises two phases, the offline and the online. In the offline phase, we prepare an ensemble speaker and speaking environment space formed by a collection of super-vectors.Each super-vector consists of the entire set of means from all the Gaussian mixture components of a set of Hidden Markov models that characterizes a particular environment. In the online phase, with the ensemble environment space prepared in the offline phase, we estimate the super-vector for a new testing environment based on a stochastic matching criterion. In this paper, we focus on methods for enhancing the construction and coverage of the environment space in the offline phase.We first demonstrate environment clustering and partitioning algorithms to structure the environment space well; then, we propose a minimum classification error training algorithm to enhance discrimination across environment super-vectors and therefore broaden the coverage of the ensemble environment space. Index Terms—Environment modeling, noise robustness.


    Access

    Download


    Export, share and cite



    Title :

    Speaker Ensembles Recognition In Different Noisy Environments


    Contributors:

    Publication date :

    2017-01-13


    Remarks:

    doi:10.26483/ijarcs.v2i6.905
    International Journal of Advanced Research in Computer Science; Vol 2, No 6 (2011): November-December 2011; 319-325 ; 0976-5697 ; 10.26483/ijarcs.v2i6



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629



    Speaker Recognition

    Gonzalez-Rodriguez, J. | Online Contents | 2007


    Robust speech detection for noisy environments

    Varela, O. / San-Segundo, R. / Hernandez, L. A. | IEEE | 2011


    Boosted ECOC ensembles for face recognition

    Windeatt, T. / Ardeshir, G. / Institution of Electrical Engineers | British Library Conference Proceedings | 2003


    Robust Speech Detection for Noisy Environments

    Varela, O | Online Contents | 2011


    Modulation Recognition Based on Neural Network Ensembles

    Ma, Xiaobo / Zhang, Bangnig / Guo, Daoxing et al. | Springer Verlag | 2021