Gloss-free Argentinian Sign Language Translation with pose-based deep learning models

Autores
Dal Bianco, Pedro Alejandro; Ríos, Gastón Gustavo; Hasperué, Waldo; Stanchi, Oscar Agustín; Ronchetti, Franco; Quiroga, Facundo Manuel
Año de publicación
2024
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
The main challenge of automatic Sign Language Translation (SLT) is obtaining data to train models. For Argentinian Sign Language (LSA), the only dataset available for SLT is LSA-T, which contains extracts of a news channel in LSA and the corresponding Spanish subtitles provided by the authors. LSA-T contains a wide variety of signers, scenarios, and lightnings that could bias a model trained on it. We propose a model for Argentinian gloss-free SLT, since LSA-T does not contain gloss representations of the signs. The model is also pose-based to improve performance on low resource devices. Different versions of the model are also tested in two other well-known datasets to compare the results: GSL and RWTH Phoenix Weather 2014T. Our model stablished the new SoTA over LSA-T, which proved to be the most challenging due to the variety of topics covered that result in a vast vocabulary with many words appearing few times.
Red de Universidades con Carreras en Informática
Materia
Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/176192
Acceder
id SEDICI_e12b68460ef0d43b4e80ce470dace89f
oai_identifier_str oai:sedici.unlp.edu.ar:10915/176192
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Gloss-free Argentinian Sign Language Translation with pose-based deep learning modelsDal Bianco, Pedro AlejandroRíos, Gastón GustavoHasperué, WaldoStanchi, Oscar AgustínRonchetti, FrancoQuiroga, Facundo ManuelCiencias InformáticasSign Language TranslationPose EstimationSign Language DatasetsDeep LearningGloss-freeThe main challenge of automatic Sign Language Translation (SLT) is obtaining data to train models. For Argentinian Sign Language (LSA), the only dataset available for SLT is LSA-T, which contains extracts of a news channel in LSA and the corresponding Spanish subtitles provided by the authors. LSA-T contains a wide variety of signers, scenarios, and lightnings that could bias a model trained on it. We propose a model for Argentinian gloss-free SLT, since LSA-T does not contain gloss representations of the signs. The model is also pose-based to improve performance on low resource devices. Different versions of the model are also tested in two other well-known datasets to compare the results: GSL and RWTH Phoenix Weather 2014T. Our model stablished the new SoTA over LSA-T, which proved to be the most challenging due to the variety of topics covered that result in a vast vocabulary with many words appearing few times.Red de Universidades con Carreras en Informática2024-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf64-71http://sedici.unlp.edu.ar/handle/10915/176192enginfo:eu-repo/semantics/altIdentifier/isbn/978-950-34-2428-5info:eu-repo/semantics/reference/hdl/10915/172755info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-10T12:50:15Zoai:sedici.unlp.edu.ar:10915/176192Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-10 12:50:15.991SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
title Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
spellingShingle Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
Dal Bianco, Pedro Alejandro
Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
title_short Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
title_full Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
title_fullStr Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
title_full_unstemmed Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
title_sort Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
dc.creator.none.fl_str_mv Dal Bianco, Pedro Alejandro
Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
author Dal Bianco, Pedro Alejandro
author_facet Dal Bianco, Pedro Alejandro
Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
author_role author
author2 Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
topic Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
dc.description.none.fl_txt_mv The main challenge of automatic Sign Language Translation (SLT) is obtaining data to train models. For Argentinian Sign Language (LSA), the only dataset available for SLT is LSA-T, which contains extracts of a news channel in LSA and the corresponding Spanish subtitles provided by the authors. LSA-T contains a wide variety of signers, scenarios, and lightnings that could bias a model trained on it. We propose a model for Argentinian gloss-free SLT, since LSA-T does not contain gloss representations of the signs. The model is also pose-based to improve performance on low resource devices. Different versions of the model are also tested in two other well-known datasets to compare the results: GSL and RWTH Phoenix Weather 2014T. Our model stablished the new SoTA over LSA-T, which proved to be the most challenging due to the variety of topics covered that result in a vast vocabulary with many words appearing few times.
Red de Universidades con Carreras en Informática
description The main challenge of automatic Sign Language Translation (SLT) is obtaining data to train models. For Argentinian Sign Language (LSA), the only dataset available for SLT is LSA-T, which contains extracts of a news channel in LSA and the corresponding Spanish subtitles provided by the authors. LSA-T contains a wide variety of signers, scenarios, and lightnings that could bias a model trained on it. We propose a model for Argentinian gloss-free SLT, since LSA-T does not contain gloss representations of the signs. The model is also pose-based to improve performance on low resource devices. Different versions of the model are also tested in two other well-known datasets to compare the results: GSL and RWTH Phoenix Weather 2014T. Our model stablished the new SoTA over LSA-T, which proved to be the most challenging due to the variety of topics covered that result in a vast vocabulary with many words appearing few times.
publishDate 2024
dc.date.none.fl_str_mv 2024-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/176192
url http://sedici.unlp.edu.ar/handle/10915/176192
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/isbn/978-950-34-2428-5
info:eu-repo/semantics/reference/hdl/10915/172755
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
64-71
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1842904747510595584
score 12.993085

Publicaciones similares