Presentation 2004/1/9
Speech Enhancement Using Spectral Subtraction and Sub-Band Decomposition with Reduced Computational Complexity
Takaaki ISHII, Yoshihiro SHIOZAWA, Nobuaki TAKAHASHI, Tsuyoshi TAKEBE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Spectral subtraction method, requiring about the same computation as high-speed convolution, suppresses stationary noise from speech by subtracting the spectral noise bias calculated during nonspeech activity. In this paper, in order to reduce the computational complexity and over estimatimation of noise, speech enhancement method using spectral subtraction and sub-band decomposition is proposed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech enhancement / spectral subtraction / perfect reconstruction
Paper # DPS2003-193,SAT2003-190,RCS2003-288
Date of Issue

Conference Information
Committee SAT
Conference Date 2004/1/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Satellite Telecommunications (SAT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech Enhancement Using Spectral Subtraction and Sub-Band Decomposition with Reduced Computational Complexity
Sub Title (in English)
Keyword(1) speech enhancement
Keyword(2) spectral subtraction
Keyword(3) perfect reconstruction
1st Author's Name Takaaki ISHII
1st Author's Affiliation Toukai University()
2nd Author's Name Yoshihiro SHIOZAWA
2nd Author's Affiliation Toukai University
3rd Author's Name Nobuaki TAKAHASHI
3rd Author's Affiliation Toukai University
4th Author's Name Tsuyoshi TAKEBE
4th Author's Affiliation Kanazawa Institute of technology
Date 2004/1/9
Paper # DPS2003-193,SAT2003-190,RCS2003-288
Volume (vol) vol.103
Number (no) 550
Page pp.pp.-
#Pages 5
Date of Issue