Advanced

Speech Enhancement Employing Adaptive Beamformer with Recursively Updated Soft Constraints

Dam, Hai Quang ; Nordholm, Sven; Grbic, Nedelko LU and Dam, Hai H. (2003) International Workshop on Acoustic Echo and Noise Control (IIWAENC 2003) In Proceedings of the International Workshop on Acoustic Echo and Noise Control (IIWAENC 2003) 9. p.307-310
Abstract
A novel adaptive beamformer employing recursively updated soft constraints for acoustic speech enhancement is proposed. The beamformer operates in a subband structure to allow a time-frequency operation for each channel. Consequently, the processing performed can be viewed as a combined weighted spatial,frequency and temporal filter. The major benefit of the new recursive soft constrained beamformer is that it allows the possibility of using the spectral information of the desired source to modify the soft constraint. This has clear benefits on the speech distortion of the source of interest. The novel adaptive beamformer involves continuous modification of the soft constraint by feeding back the spectral content of the estimated output speech... (More)
A novel adaptive beamformer employing recursively updated soft constraints for acoustic speech enhancement is proposed. The beamformer operates in a subband structure to allow a time-frequency operation for each channel. Consequently, the processing performed can be viewed as a combined weighted spatial,frequency and temporal filter. The major benefit of the new recursive soft constrained beamformer is that it allows the possibility of using the spectral information of the desired source to modify the soft constraint. This has clear benefits on the speech distortion of the source of interest. The novel adaptive beamformer involves continuous modification of the soft constraint by feeding back the spectral content of the estimated output speech signal. Evaluations of the proposed beamformer based on real car data show that the proposed algorithm significantly improves the speech quality with noise suppression levels up to 17 dB.
(Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of the International Workshop on Acoustic Echo and Noise Control (IIWAENC 2003)
volume
9
pages
4 pages
conference name
International Workshop on Acoustic Echo and Noise Control (IIWAENC 2003)
ISBN
4-9901531-3-8
language
English
LU publication?
no
id
624056c8-b6fe-4729-b1d1-2c6144ccf170
alternative location
http://www.kecl.ntt.co.jp/icl/signal/iwaenc03/cdrom/data/0047.pdf
date added to LUP
2016-06-23 15:42:35
date last changed
2016-06-29 12:12:42
@misc{624056c8-b6fe-4729-b1d1-2c6144ccf170,
  abstract     = {A novel adaptive beamformer employing recursively updated soft constraints for acoustic speech enhancement is proposed. The beamformer operates in a subband structure to allow a time-frequency operation for each channel. Consequently, the processing performed can be viewed as a combined weighted spatial,frequency and temporal filter. The major benefit of the new recursive soft constrained beamformer is that it allows the possibility of using the spectral information of the desired source to modify the soft constraint. This has clear benefits on the speech distortion of the source of interest. The novel adaptive beamformer involves continuous modification of the soft constraint by feeding back the spectral content of the estimated output speech signal. Evaluations of the proposed beamformer based on real car data show that the proposed algorithm significantly improves the speech quality with noise suppression levels up to 17 dB.<br/>},
  author       = {Dam, Hai Quang  and Nordholm, Sven and Grbic, Nedelko and Dam, Hai H.},
  isbn         = { 4-9901531-3-8},
  language     = {eng},
  pages        = {307--310},
  series       = {Proceedings of the International Workshop on Acoustic Echo and Noise Control (IIWAENC 2003)},
  title        = {Speech Enhancement Employing Adaptive Beamformer with Recursively Updated Soft Constraints},
  volume       = {9},
  year         = {2003},
}