• DocumentCode
    3046277
  • Title

    Detection and removal of impulsive colored noise for speech enhancement

  • Author

    He, Zhiyong ; Guo, Xuhong ; Zhang, Maoqing

  • Author_Institution
    Sch. of Mech. & Electr. Eng., Soochow Univ., Suzhou, China
  • fYear
    2010
  • fDate
    20-23 June 2010
  • Firstpage
    2320
  • Lastpage
    2324
  • Abstract
    Speech enhancement aims at denoising noisy speech signal and to extract the clean speech. In this work, impulsive colored noise is regarded. The detail coefficient from discrete wavelet transform is used to analyze the distribution of impulsive colored noise in time domain. The energy of impulsive colored noise in different frequency bands can be used to find thresholds for wavelet thresholding techniques. The efficiency of the algorithm is evaluated.
  • Keywords
    signal denoising; speech enhancement; wavelet transforms; impulsive colored noise detection; impulsive colored noise removal; noisy speech signal denoising; speech enhancement; wavelet thresholding; Additive white noise; Colored noise; Discrete wavelet transforms; Gaussian noise; Noise reduction; Speech analysis; Speech enhancement; Time domain analysis; Wavelet domain; Working environment noise;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information and Automation (ICIA), 2010 IEEE International Conference on
  • Conference_Location
    Harbin
  • Print_ISBN
    978-1-4244-5701-4
  • Type

    conf

  • DOI
    10.1109/ICINFA.2010.5512179
  • Filename
    5512179