Speech recognition enhancement using beamforming and a genetic algorithm

This paper proposes a genetic algorithm (GA) based beamformer to optimize speech recognition accuracy for a pretrained speech recognizer. The proposed beamformer is designed to tackle the non-differentiable and non-linear natures of speech recognition by employing the GA algorithm to search for the...

Full description

Bibliographic Details
Main Authors: Chan, Kit Yan, Yiu, Ka Fai, Low, Siow, Nordholm, Sven, Ling, S.
Other Authors: Wanlei Zhou
Format: Conference Paper
Published: IEEE Computer Society 2009
Subjects:
Online Access:http://doi.ieeecomputersociety.org/10.1109/NSS.2009.44
http://hdl.handle.net/20.500.11937/37617
_version_ 1848755098393509888
author Chan, Kit Yan
Yiu, Ka Fai
Low, Siow
Nordholm, Sven
Ling, S.
author2 Wanlei Zhou
author_facet Wanlei Zhou
Chan, Kit Yan
Yiu, Ka Fai
Low, Siow
Nordholm, Sven
Ling, S.
author_sort Chan, Kit Yan
building Curtin Institutional Repository
collection Online Access
description This paper proposes a genetic algorithm (GA) based beamformer to optimize speech recognition accuracy for a pretrained speech recognizer. The proposed beamformer is designed to tackle the non-differentiable and non-linear natures of speech recognition by employing the GA algorithm to search for the optimal beamformer weights. Specifically, a population of beamformer weights is reproduced by crossover and mutation until the optimal beamformer weights are obtained. Results show that the speech recognition accuracies can be greatly improved even in noisy environments.
first_indexed 2025-11-14T08:50:54Z
format Conference Paper
id curtin-20.500.11937-37617
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:50:54Z
publishDate 2009
publisher IEEE Computer Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-376172019-02-19T05:35:06Z Speech recognition enhancement using beamforming and a genetic algorithm Chan, Kit Yan Yiu, Ka Fai Low, Siow Nordholm, Sven Ling, S. Wanlei Zhou beamforming genetic algorithm Speech recognition signal enhancement This paper proposes a genetic algorithm (GA) based beamformer to optimize speech recognition accuracy for a pretrained speech recognizer. The proposed beamformer is designed to tackle the non-differentiable and non-linear natures of speech recognition by employing the GA algorithm to search for the optimal beamformer weights. Specifically, a population of beamformer weights is reproduced by crossover and mutation until the optimal beamformer weights are obtained. Results show that the speech recognition accuracies can be greatly improved even in noisy environments. 2009 Conference Paper http://hdl.handle.net/20.500.11937/37617 http://doi.ieeecomputersociety.org/10.1109/NSS.2009.44 IEEE Computer Society fulltext
spellingShingle beamforming
genetic algorithm
Speech recognition
signal enhancement
Chan, Kit Yan
Yiu, Ka Fai
Low, Siow
Nordholm, Sven
Ling, S.
Speech recognition enhancement using beamforming and a genetic algorithm
title Speech recognition enhancement using beamforming and a genetic algorithm
title_full Speech recognition enhancement using beamforming and a genetic algorithm
title_fullStr Speech recognition enhancement using beamforming and a genetic algorithm
title_full_unstemmed Speech recognition enhancement using beamforming and a genetic algorithm
title_short Speech recognition enhancement using beamforming and a genetic algorithm
title_sort speech recognition enhancement using beamforming and a genetic algorithm
topic beamforming
genetic algorithm
Speech recognition
signal enhancement
url http://doi.ieeecomputersociety.org/10.1109/NSS.2009.44
http://hdl.handle.net/20.500.11937/37617