Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

An Adaptive Blind Beamformer with an Integrated Single-channel Noise Reduction Method for Robust Real-time Blind Speech Extraction

Sällberg, Benny ; Grbic, Nedelko LU and Claesson, Ingvar LU (2008) IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008 p.309-312
Abstract
The performance of single-channel temporal noise reduction methods generally deteriorate in high noise environments, whereas spatial beamformers can maintain some level of speech enhancement. This paper presents a solution where a low complexity single-channel noise reduction method is integrated into the feedback control loop of an adaptive blind beamformer with the purpose of robust blind speech extraction in high noise environments. The proposed combined system outperforms each of the individual methods with respect to signal-to-interference ratio improvement for a wide range of operating conditions, and where the loss in estimated perceptual speech quality due to the combined system is tolerably low. Furthermore, the excess processing... (More)
The performance of single-channel temporal noise reduction methods generally deteriorate in high noise environments, whereas spatial beamformers can maintain some level of speech enhancement. This paper presents a solution where a low complexity single-channel noise reduction method is integrated into the feedback control loop of an adaptive blind beamformer with the purpose of robust blind speech extraction in high noise environments. The proposed combined system outperforms each of the individual methods with respect to signal-to-interference ratio improvement for a wide range of operating conditions, and where the loss in estimated perceptual speech quality due to the combined system is tolerably low. Furthermore, the excess processing load in a hardware solution is comparatively insignificant for the proposed extended approach. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2008 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)
pages
4 pages
conference name
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008
conference location
Las Vegas, NV, United States
conference dates
2008-03-31 - 2008-04-04
external identifiers
  • scopus:51449117385
ISBN
978-1-4244-1483-3
978-1-4244-1484-0
DOI
10.1109/ICASSP.2008.4517608
language
English
LU publication?
yes
id
07156c6b-20dd-45ba-ae12-5bf22d66d0ee
date added to LUP
2016-06-23 16:57:05
date last changed
2024-01-04 08:58:51
@inproceedings{07156c6b-20dd-45ba-ae12-5bf22d66d0ee,
  abstract     = {{The performance of single-channel temporal noise reduction methods generally deteriorate in high noise environments, whereas spatial beamformers can maintain some level of speech enhancement. This paper presents a solution where a low complexity single-channel noise reduction method is integrated into the feedback control loop of an adaptive blind beamformer with the purpose of robust blind speech extraction in high noise environments. The proposed combined system outperforms each of the individual methods with respect to signal-to-interference ratio improvement for a wide range of operating conditions, and where the loss in estimated perceptual speech quality due to the combined system is tolerably low. Furthermore, the excess processing load in a hardware solution is comparatively insignificant for the proposed extended approach.}},
  author       = {{Sällberg, Benny and Grbic, Nedelko and Claesson, Ingvar}},
  booktitle    = {{2008 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}},
  isbn         = {{978-1-4244-1483-3}},
  language     = {{eng}},
  pages        = {{309--312}},
  title        = {{An Adaptive Blind Beamformer with an Integrated Single-channel Noise Reduction Method for Robust Real-time Blind Speech Extraction}},
  url          = {{http://dx.doi.org/10.1109/ICASSP.2008.4517608}},
  doi          = {{10.1109/ICASSP.2008.4517608}},
  year         = {{2008}},
}