New modified Bat algorithm for blind speech enhancement in time domain

We address the speech enhancement problem for dual convolutif mixed channel by viewing it in a blind separation sources setting. One widely used technique to separate mixed signals is to apply adaptive filtering, the challenge is to identify an unknown finite impulse response. traditionally we apply...

Descripción completa

Detalles Bibliográficos
Autores: Fisli, Sofiane, Djendi, Mohamed
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:México
Institución:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
Repositorio:Journal of Applied Research and Technology
Idioma:inglés
OAI Identifier:oai:ojs2.localhost:article/1931
Acceso en línea:https://jart.icat.unam.mx/index.php/jart/article/view/1931
Access Level:acceso abierto
Palabra clave:Speech enhancement
blind source separation
population-based metaheuristic algorithms
system misalignment
segmental signal-to-noise ratio
id MX_f68bcbe4bd877607dca6b6561baa0e57
oai_identifier_str oai:ojs2.localhost:article/1931
network_acronym_str MX
network_name_str México
repository_id_str
spelling New modified Bat algorithm for blind speech enhancement in time domainFisli, SofianeDjendi, MohamedSpeech enhancementblind source separationpopulation-based metaheuristic algorithmssystem misalignmentsegmental signal-to-noise ratioWe address the speech enhancement problem for dual convolutif mixed channel by viewing it in a blind separation sources setting. One widely used technique to separate mixed signals is to apply adaptive filtering, the challenge is to identify an unknown finite impulse response. traditionally we apply a gradient-based algorithm to adapt filter coefficients. However, such algorithm often suffers from premature convergence ,when using large filters and non-stationary inputs ,  leading to the so-called local minimum problem , which affects the quality of  enhanced signals significatively .one alternative to overcome this problem is to apply a population-based metaheuristic algorithms in which filter coefficients are adapted iteratively  by minimizing a cost function .But even with this metaheuristic based solution, local minimum problem at large filters still exists. In order to avoid local minima and improve the chance to reach the global solution, we propose in this paper, a novel algorithm called a modified bat algorithm to render the search process efficiently by enhancing its capability of exploration and exploitation. Several experiments under different noise types are carried out using our proposed modified bat algorithm in comparison with some of the popular state-of-the-art algorithms. The enhanced signals obtained by each algorithm at the separation process outputs, show good behavior and superiority of our proposed algorithm. In terms of system misalignment, as well as a segmental signal-to-noise ratio.Universidad Nacional Autónoma de México2023-12-15info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionPeer-reviewed Articleapplication/pdfhttps://jart.icat.unam.mx/index.php/jart/article/view/193110.22201/icat.24486736e.2023.21.6.1931Journal of Applied Research and Technology; Vol. 21 No. 6 (2023); 982-990Journal of Applied Research and Technology; Vol. 21 Núm. 6 (2023); 982-9902448-67361665-642310.22201/icat.24486736e.2023.21.6reponame:Journal of Applied Research and Technologyinstname:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICOinstacron:UNAMenghttps://jart.icat.unam.mx/index.php/jart/article/view/1931/1062Copyright (c) 2023 Universidad Nacional Autónoma de Méxicohttp://creativecommons.org/licenses/by-nc-nd/4.0info:eu-repo/semantics/openAccessoai:ojs2.localhost:article/19312024-08-16T17:54:20Z
dc.title.none.fl_str_mv New modified Bat algorithm for blind speech enhancement in time domain
title New modified Bat algorithm for blind speech enhancement in time domain
spellingShingle New modified Bat algorithm for blind speech enhancement in time domain
Fisli, Sofiane
Speech enhancement
blind source separation
population-based metaheuristic algorithms
system misalignment
segmental signal-to-noise ratio
title_short New modified Bat algorithm for blind speech enhancement in time domain
title_full New modified Bat algorithm for blind speech enhancement in time domain
title_fullStr New modified Bat algorithm for blind speech enhancement in time domain
title_full_unstemmed New modified Bat algorithm for blind speech enhancement in time domain
title_sort New modified Bat algorithm for blind speech enhancement in time domain
dc.creator.none.fl_str_mv Fisli, Sofiane
Djendi, Mohamed
author Fisli, Sofiane
author_facet Fisli, Sofiane
Djendi, Mohamed
author_role author
author2 Djendi, Mohamed
author2_role author
dc.subject.none.fl_str_mv Speech enhancement
blind source separation
population-based metaheuristic algorithms
system misalignment
segmental signal-to-noise ratio
topic Speech enhancement
blind source separation
population-based metaheuristic algorithms
system misalignment
segmental signal-to-noise ratio
description We address the speech enhancement problem for dual convolutif mixed channel by viewing it in a blind separation sources setting. One widely used technique to separate mixed signals is to apply adaptive filtering, the challenge is to identify an unknown finite impulse response. traditionally we apply a gradient-based algorithm to adapt filter coefficients. However, such algorithm often suffers from premature convergence ,when using large filters and non-stationary inputs ,  leading to the so-called local minimum problem , which affects the quality of  enhanced signals significatively .one alternative to overcome this problem is to apply a population-based metaheuristic algorithms in which filter coefficients are adapted iteratively  by minimizing a cost function .But even with this metaheuristic based solution, local minimum problem at large filters still exists. In order to avoid local minima and improve the chance to reach the global solution, we propose in this paper, a novel algorithm called a modified bat algorithm to render the search process efficiently by enhancing its capability of exploration and exploitation. Several experiments under different noise types are carried out using our proposed modified bat algorithm in comparison with some of the popular state-of-the-art algorithms. The enhanced signals obtained by each algorithm at the separation process outputs, show good behavior and superiority of our proposed algorithm. In terms of system misalignment, as well as a segmental signal-to-noise ratio.
publishDate 2023
dc.date.none.fl_str_mv 2023-12-15
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://jart.icat.unam.mx/index.php/jart/article/view/1931
10.22201/icat.24486736e.2023.21.6.1931
url https://jart.icat.unam.mx/index.php/jart/article/view/1931
identifier_str_mv 10.22201/icat.24486736e.2023.21.6.1931
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://jart.icat.unam.mx/index.php/jart/article/view/1931/1062
dc.rights.none.fl_str_mv Copyright (c) 2023 Universidad Nacional Autónoma de México
http://creativecommons.org/licenses/by-nc-nd/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2023 Universidad Nacional Autónoma de México
http://creativecommons.org/licenses/by-nc-nd/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidad Nacional Autónoma de México
publisher.none.fl_str_mv Universidad Nacional Autónoma de México
dc.source.none.fl_str_mv Journal of Applied Research and Technology; Vol. 21 No. 6 (2023); 982-990
Journal of Applied Research and Technology; Vol. 21 Núm. 6 (2023); 982-990
2448-6736
1665-6423
10.22201/icat.24486736e.2023.21.6
reponame:Journal of Applied Research and Technology
instname:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
instacron:UNAM
instname_str UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
instacron_str UNAM
institution UNAM
reponame_str Journal of Applied Research and Technology
collection Journal of Applied Research and Technology
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858177704914845696
score 15,81155

Similares en LA Referencia