• DocumentCode
    3010172
  • Title

    A spectral subtraction method for noise reduction in speech signals

  • Author

    Mwema, Wilfred N. ; Mwangi, Elijah

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Nairobi Univ., Kenya
  • Volume
    1
  • fYear
    1996
  • fDate
    24-27 Sep 1996
  • Firstpage
    382
  • Abstract
    A noise suppression algorithm for enhancing speech signals corrupted by additive white Gaussian noise is presented in this paper. The algorithm is based on the subtraction of estimated noise spectrum from the noisy speech spectrum. The performance of the algorithm is assessed by comparing the original clean speech and processed speech. An objective measure based on the log area ratios of a speech segment is used
  • Keywords
    Gaussian noise; acoustic noise; acoustic signal processing; interference suppression; spectral analysis; speech enhancement; additive white Gaussian noise; estimated noise spectrum; log area ratios; noise reduction; noise suppression algorithm; noisy speech; performance; spectral subtraction method; speech segment; speech signals; Additive noise; Gaussian noise; Microphones; Noise cancellation; Noise reduction; Signal processing; Signal processing algorithms; Signal to noise ratio; Speech enhancement; Speech processing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    AFRICON, 1996., IEEE AFRICON 4th
  • Conference_Location
    Stellenbosch
  • Print_ISBN
    0-7803-3019-6
  • Type

    conf

  • DOI
    10.1109/AFRCON.1996.563142
  • Filename
    563142