By combining Fractional Spectral Subtraction (FSS) with Perceptual Linear Predictive (PLP), a hybrid method of noise robustness speech recognition isinvestigated in this paper. This method uses FSS for noisy speech to reduce noise components in the fractional Fourier domain. According to the results ofcomputing Itakura distance and Mean Square Error (MSE), an approximate optimal fractional order is then obtained by comparing the difference betweenthem. Perceptual Linear Predictive Cepstral Coefficients (PLPCC) is finally computed for the enhanced speech in terms of the above obtained order.It is shown that this hybrid method performs better compared with conventional spectral subtraction and PLPCC for digits speech recognition experiments. Moreover, this method denotes good noise robustness when noise levels increases.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Hybrid Method of Noise Robust Speech Recognition Based on Fractional Spectral Subtraction and Perceptual Linear Preditive


    Contributors:


    Publication date :

    2008-05-01


    Size :

    262373 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    FPGA implementation of spectral subtraction for automotive speech recognition

    Whittington, Jim / Deo, Kapeel / Kleinschmidt, Tristan et al. | IEEE | 2009


    FPGA implementation of spectral subtraction for in-car speech enhancement and recognition

    Whittington, J. / Deo, K. / Kleinschmidt, T. et al. | Tema Archive | 2008


    Switching linear dynamic models for noise robust in-car speech recognition

    Schuller, Björn / Wöllmer, Martin / Moosmayr, Tobias et al. | Tema Archive | 2008


    Enhancement of Non-air Conduct Speech Based on Multi-band Spectral Subtraction Method

    Li, Sheng / Niu, Ming / Wang, JianQi et al. | IEEE | 2008


    Noise Robust Speech Recognition Using Prosodic Information

    Iwano, Koji / Seki, Takahiro / Furui, Sadaoki | Springer Verlag | 2005