Acoustic source localization with deep generalized cross correlations

One of the most popular techniques for Acoustic Source Localization is the Generalized Cross Correlation (GCC) and its use in Steered Response Power techniques (SRP). Nowadays, Deep Learning strategies may outperform these classical methods, but they are generally dependent on the room and sensor ge...

Descripción completa

Detalles Bibliográficos
Autores: Vera Díaz, Juan Manuel|||0000-0002-6152-5789, Pizarro Pérez, Daniel|||0000-0003-0622-4884, Macías Guarasa, Javier|||0000-0002-3303-3963
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/64485
Acceso en línea:http://hdl.handle.net/10017/64485
https://dx.doi.org/10.1016/j.sigpro.2021.108169
Access Level:acceso abierto
Palabra clave:Acoustic source localization
Deep learning
Generalized cross correlation
Beamforming
SRP-PHAT
Lasso
Electrónica
Electronics
id ES_2c7fef3d309fc97de9b2be07d1593842
oai_identifier_str oai:ebuah.uah.es:10017/64485
network_acronym_str ES
network_name_str España
repository_id_str
spelling Acoustic source localization with deep generalized cross correlationsVera Díaz, Juan Manuel|||0000-0002-6152-5789Pizarro Pérez, Daniel|||0000-0003-0622-4884Macías Guarasa, Javier|||0000-0002-3303-3963Acoustic source localizationDeep learningGeneralized cross correlationBeamformingSRP-PHATLassoElectrónicaElectronicsOne of the most popular techniques for Acoustic Source Localization is the Generalized Cross Correlation (GCC) and its use in Steered Response Power techniques (SRP). Nowadays, Deep Learning strategies may outperform these classical methods, but they are generally dependent on the room and sensor geometric configuration that are used during the training phases. Hence, they require adaptation and re-training when facing a new environment, which is a problem in practice as re-training requires labelling new data and running a complex training algorithm. In this work we use a Convolutional Deep Neural Network that transforms the GCC between two signals into a Gaussian shaped signal, that we call Deep Generalized Cross Correlation (DeepGCC). We combine DeepGCC estimations to create a 3D acoustic map, similarly to SRP techniques. This acoustic map can be further refined using a sparse generative model to recover the source position. Crucially, we can adapt the acoustic map to different microphone array geometries without retraining the DeepGCC network. We show that our method outperforms both classical approaches and recent Deep Learning strategies in real and simulated challenging scenarios with mismatched training-testing conditions, not requiring re-training with different sensor configurations or room environments.Ministerio de Economía y CompetitividadAgencia Estatal de InvestigaciónUniversidad de AlcaláElsevier20212021-10-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/64485https://dx.doi.org/10.1016/j.sigpro.2021.108169reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)InglésengMinisterio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TIN2016-75982-C2-1-R DETECCION SEMANTICA MULTISENSORIAL DE SITUACIONES ANOMALAS EN ENTORNOS SIN RESTRICCIONESAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2016-80939-R RECONSTRUCCION DE OBJETOS DEFORMABLES A PARTIR DE IMAGENES Y SUS APLICACIONES A LA REALIDAD AUMENTADA EN CIRUGIA MINIMAMENTE INVASIVAUAH Not available CCG2018%2FEXP-019UAH Not available CCG2019%2FIA-024UAH Not available CCG2020%2FIA-043open accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/644852026-06-18T11:13:07Z
dc.title.none.fl_str_mv Acoustic source localization with deep generalized cross correlations
title Acoustic source localization with deep generalized cross correlations
spellingShingle Acoustic source localization with deep generalized cross correlations
Vera Díaz, Juan Manuel|||0000-0002-6152-5789
Acoustic source localization
Deep learning
Generalized cross correlation
Beamforming
SRP-PHAT
Lasso
Electrónica
Electronics
title_short Acoustic source localization with deep generalized cross correlations
title_full Acoustic source localization with deep generalized cross correlations
title_fullStr Acoustic source localization with deep generalized cross correlations
title_full_unstemmed Acoustic source localization with deep generalized cross correlations
title_sort Acoustic source localization with deep generalized cross correlations
dc.creator.none.fl_str_mv Vera Díaz, Juan Manuel|||0000-0002-6152-5789
Pizarro Pérez, Daniel|||0000-0003-0622-4884
Macías Guarasa, Javier|||0000-0002-3303-3963
author Vera Díaz, Juan Manuel|||0000-0002-6152-5789
author_facet Vera Díaz, Juan Manuel|||0000-0002-6152-5789
Pizarro Pérez, Daniel|||0000-0003-0622-4884
Macías Guarasa, Javier|||0000-0002-3303-3963
author_role author
author2 Pizarro Pérez, Daniel|||0000-0003-0622-4884
Macías Guarasa, Javier|||0000-0002-3303-3963
author2_role author
author
dc.subject.none.fl_str_mv Acoustic source localization
Deep learning
Generalized cross correlation
Beamforming
SRP-PHAT
Lasso
Electrónica
Electronics
topic Acoustic source localization
Deep learning
Generalized cross correlation
Beamforming
SRP-PHAT
Lasso
Electrónica
Electronics
description One of the most popular techniques for Acoustic Source Localization is the Generalized Cross Correlation (GCC) and its use in Steered Response Power techniques (SRP). Nowadays, Deep Learning strategies may outperform these classical methods, but they are generally dependent on the room and sensor geometric configuration that are used during the training phases. Hence, they require adaptation and re-training when facing a new environment, which is a problem in practice as re-training requires labelling new data and running a complex training algorithm. In this work we use a Convolutional Deep Neural Network that transforms the GCC between two signals into a Gaussian shaped signal, that we call Deep Generalized Cross Correlation (DeepGCC). We combine DeepGCC estimations to create a 3D acoustic map, similarly to SRP techniques. This acoustic map can be further refined using a sparse generative model to recover the source position. Crucially, we can adapt the acoustic map to different microphone array geometries without retraining the DeepGCC network. We show that our method outperforms both classical approaches and recent Deep Learning strategies in real and simulated challenging scenarios with mismatched training-testing conditions, not requiring re-training with different sensor configurations or room environments.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-10-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/64485
https://dx.doi.org/10.1016/j.sigpro.2021.108169
url http://hdl.handle.net/10017/64485
https://dx.doi.org/10.1016/j.sigpro.2021.108169
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TIN2016-75982-C2-1-R DETECCION SEMANTICA MULTISENSORIAL DE SITUACIONES ANOMALAS EN ENTORNOS SIN RESTRICCIONES
Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2016-80939-R RECONSTRUCCION DE OBJETOS DEFORMABLES A PARTIR DE IMAGENES Y SUS APLICACIONES A LA REALIDAD AUMENTADA EN CIRUGIA MINIMAMENTE INVASIVA
UAH Not available CCG2018%2FEXP-019
UAH Not available CCG2019%2FIA-024
UAH Not available CCG2020%2FIA-043
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
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 Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405245897965568
score 15,811543

Similares en LA Referencia