The spread of speech is not only depending upon the air, but by means of other medium. This study reports a new speech detecting method by using EMW Radar. However, the combined noise which is added in the detected speech decreased the speech quality to a large extent, since noise is mostly colored and does not affect the speech signal uniformly over the entire spectrum. This study, therefore, propose a multi-band spectral subtraction approach which takes into account the fact that colored noise affects the speech spectrum differently at various frequencies. The results suggest that this method achieves a better reduction of the whole-frequency noise, as well as musical noise, and yields good speech quality.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Li, Sheng (author) / Niu, Ming (author) / Wang, JianQi (author) / Liu, Tian (author) / Jing, XiJing (author)


    Publication date :

    2008-05-01


    Size :

    945173 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



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

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


    FPGA implementation of spectral subtraction for automotive speech recognition

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




    Speech enhancement with sub-band processing in an automobile environment

    Campbell,D.R. / Toner,E. / Univ.of Paisley,GB | Automotive engineering | 1993