Spatial Filter Bank Design for Speech Enhancement Beamforming Applications

Zohra Yermeche; Per Cornelius; Nedelko Grbic; Ingvar Claesson

doi:10.1109/SAM.2004.1503010

Spatial Filter Bank Design for Speech Enhancement Beamforming Applications

Zohra Yermeche, Per Cornelius, Nedelko Grbic, Ingvar Claesson

Department of Electrical and Information Technology

Blekinge Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

In this paper, a new spatial filter bank design method for speech enhancement beamforming applications is presented. The aim of this design is to construct a set of different filter banks that would include the constraint of signal passage at one position (and closing in other positions corresponding to known disturbing sources). By performing the directional opening towards the desired location in the fixed filter bank structure, the beamformer is left with the task of tracking and suppressing the continuously emerging noise sources. This algorithm has been implemented in MATLAB and tested on real speech recordings conducted in a car hands-free communication situation. Results show that a reduction of the total complexity can be achieved while maintaining the noise suppression performance and reducing the speech distortion.

Original language	English
Title of host publication	Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2004
Pages	557-560
Number of pages	4
DOIs	https://doi.org/10.1109/SAM.2004.1503010
Publication status	Published - 2004 Jul
Event	2004 IEEE Sensor Array and Multichannel Signal Processing Workshop - Barcelona, Spain Duration: 2004 Jul 18 → 2004 Jul 21

Workshop

Workshop	2004 IEEE Sensor Array and Multichannel Signal Processing Workshop
Country/Territory	Spain
City	Barcelona
Period	2004/07/18 → 2004/07/21

Subject classification (UKÄ)

Signal Processing

Access to Document

10.1109/SAM.2004.1503010

Cite this

@inproceedings{6a718ae964cc42e3958b40887b01f383,

title = "Spatial Filter Bank Design for Speech Enhancement Beamforming Applications",

abstract = "In this paper, a new spatial filter bank design method for speech enhancement beamforming applications is presented. The aim of this design is to construct a set of different filter banks that would include the constraint of signal passage at one position (and closing in other positions corresponding to known disturbing sources). By performing the directional opening towards the desired location in the fixed filter bank structure, the beamformer is left with the task of tracking and suppressing the continuously emerging noise sources. This algorithm has been implemented in MATLAB and tested on real speech recordings conducted in a car hands-free communication situation. Results show that a reduction of the total complexity can be achieved while maintaining the noise suppression performance and reducing the speech distortion.",

author = "Zohra Yermeche and Per Cornelius and Nedelko Grbic and Ingvar Claesson",

year = "2004",

month = jul,

doi = "10.1109/SAM.2004.1503010",

language = "English",

isbn = "0-7803-8545-4",

pages = "557--560",

booktitle = "Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2004",

note = "2004 IEEE Sensor Array and Multichannel Signal Processing Workshop ; Conference date: 18-07-2004 Through 21-07-2004",

}

TY - GEN

T1 - Spatial Filter Bank Design for Speech Enhancement Beamforming Applications

AU - Yermeche, Zohra

AU - Cornelius, Per

AU - Grbic, Nedelko

AU - Claesson, Ingvar

PY - 2004/7

Y1 - 2004/7

N2 - In this paper, a new spatial filter bank design method for speech enhancement beamforming applications is presented. The aim of this design is to construct a set of different filter banks that would include the constraint of signal passage at one position (and closing in other positions corresponding to known disturbing sources). By performing the directional opening towards the desired location in the fixed filter bank structure, the beamformer is left with the task of tracking and suppressing the continuously emerging noise sources. This algorithm has been implemented in MATLAB and tested on real speech recordings conducted in a car hands-free communication situation. Results show that a reduction of the total complexity can be achieved while maintaining the noise suppression performance and reducing the speech distortion.

AB - In this paper, a new spatial filter bank design method for speech enhancement beamforming applications is presented. The aim of this design is to construct a set of different filter banks that would include the constraint of signal passage at one position (and closing in other positions corresponding to known disturbing sources). By performing the directional opening towards the desired location in the fixed filter bank structure, the beamformer is left with the task of tracking and suppressing the continuously emerging noise sources. This algorithm has been implemented in MATLAB and tested on real speech recordings conducted in a car hands-free communication situation. Results show that a reduction of the total complexity can be achieved while maintaining the noise suppression performance and reducing the speech distortion.

U2 - 10.1109/SAM.2004.1503010

DO - 10.1109/SAM.2004.1503010

M3 - Paper in conference proceeding

SN - 0-7803-8545-4

SP - 557

EP - 560

BT - Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2004

T2 - 2004 IEEE Sensor Array and Multichannel Signal Processing Workshop

Y2 - 18 July 2004 through 21 July 2004

ER -

Spatial Filter Bank Design for Speech Enhancement Beamforming Applications

Abstract

Workshop

Subject classification (UKÄ)

Access to Document

Fingerprint

Cite this