This paper presents a robust speaker identification approach basing on kernel principle component analysis (KPCA) and probabilistic neural network (PNN). KPCA is exploited to reduce the dimension of input vector and to denoise speech signal by extracting the nonlinear principle components of the feature vector. The extracted principle components are utilized as the input feature vector of the classifier and a probabilistic neural network (PNN) is designed as the classifier of identification system. We have tested our system on KING corpus and the experimental result shows that our system outperforms PNN and GMM approach in terms of robustness and training time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Application of KPCA and PNN for Robust Speaker Identification


    Contributors:
    Ren, Xue-Hui (author) / Zhang, Ya-Fen (author) / Xing, Yu-Juan (author) / Li, Ming (author)


    Publication date :

    2008-05-01


    Size :

    332734 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    The Research and Application of Vehicle Identification Using KPCA Based on the Car Networking Environment

    Xui, W. / Wang, R.C. / Huang, H.P. et al. | British Library Conference Proceedings | 2011


    The Research and Application of Vehicle Identification Using KPCA Based on the Car Networking Environment

    Xu, Wei ;Wang, Ru Chuan ;Huang, Hai Ping | Trans Tech Publications | 2011


    An Integrated Fault Identification Method Based on KPCA-PNN for Complex Industrial Process

    Bo, C.-m. / Wang, Z.-q. / Zhang, G.-m. | British Library Online Contents | 2009


    DBSCAN Based Parameter Optimization of KPCA for Fault Diagnosis

    Shaojun, Liang / Xing, Zheng / Lipeng, Xie et al. | TIBKAT | 2022


    Partially observed objects localization with PCA and KPCA models

    Romaniuk, B. / Guilloux, V. / Desvignes, M. et al. | IEEE | 2004