Presentation 2008-07-18
Frequency Domain Speech Dereverberation with Crossband Effect Compensation
Tomohiro NAKATANI, Takuya YOSHIOKA, Keisuke KINOSHITA, Masato MIYOSHI, Biing-Hwang JUANG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It has recently been shown that the maximum likelihood estimation approach with a time-varying source model is very effective in achieving speech dereverberation based only on a short observation. In addition, STFT domain processing has been shown to be promising for implementing this dereverberation approach in a computationally efficient way. This paper presents a way of further improving the STFT domain speech dereverberation in terms of both computational cost and accuracy. One important issue here is how to calculate time-domain convolution with a long filter precisely using STFT. We introduce an STFT domain filtering method with crossband effect compensation for this purpose. Experimental results show that the proposed method allows us to implement the dereverberation algorithm in the STFT domain more precisely with less computational cost than the existing method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Dereverberation / Maximum likelihood estimation / Short time Fourier transform / Crossband filtering
Paper # EA2008-43
Date of Issue

Conference Information
Committee EA
Conference Date 2008/7/11(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 Engineering Acoustics (EA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Frequency Domain Speech Dereverberation with Crossband Effect Compensation
Sub Title (in English)
Keyword(1) Dereverberation
Keyword(2) Maximum likelihood estimation
Keyword(3) Short time Fourier transform
Keyword(4) Crossband filtering
1st Author's Name Tomohiro NAKATANI
1st Author's Affiliation NTT Communication Science Laboratories., NTT Corporation()
2nd Author's Name Takuya YOSHIOKA
2nd Author's Affiliation NTT Communication Science Laboratories., NTT Corporation
3rd Author's Name Keisuke KINOSHITA
3rd Author's Affiliation NTT Communication Science Laboratories., NTT Corporation
4th Author's Name Masato MIYOSHI
4th Author's Affiliation NTT Communication Science Laboratories., NTT Corporation
5th Author's Name Biing-Hwang JUANG
5th Author's Affiliation School of ECE, Georgia Institute of Technology
Date 2008-07-18
Paper # EA2008-43
Volume (vol) vol.108
Number (no) 143
Page pp.pp.-
#Pages 6
Date of Issue