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

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...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Dal Bianco, Pedro Alejandro, Ríos, Gastón Gustavo, Hasperué, Waldo, Stanchi, Oscar Agustín, Ronchetti, Franco, Quiroga, Facundo Manuel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2024
Materias:
Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/176192
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-176192
record_format dspace
spelling I19-R120-10915-1761922025-02-06T20:05:42Z http://sedici.unlp.edu.ar/handle/10915/176192 Gloss-free Argentinian Sign Language Translation with pose-based deep learning models Dal Bianco, Pedro Alejandro Ríos, Gastón Gustavo Hasperué, Waldo Stanchi, Oscar Agustín Ronchetti, Franco Quiroga, Facundo Manuel 2024-10 2024 2025-02-06T12:34:33Z en Ciencias Informáticas Sign Language Translation Pose Estimation Sign Language Datasets Deep Learning Gloss-free 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 Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 64-71
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
spellingShingle Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
Dal Bianco, Pedro Alejandro
Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
topic_facet Ciencias Informáticas
Sign Language Translation
Pose Estimation
Sign Language Datasets
Deep Learning
Gloss-free
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.
format Objeto de conferencia
Objeto de conferencia
author Dal Bianco, Pedro Alejandro
Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
author_facet Dal Bianco, Pedro Alejandro
Ríos, Gastón Gustavo
Hasperué, Waldo
Stanchi, Oscar Agustín
Ronchetti, Franco
Quiroga, Facundo Manuel
author_sort Dal Bianco, Pedro Alejandro
title Gloss-free Argentinian Sign Language Translation with pose-based deep learning models
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
publishDate 2024
url http://sedici.unlp.edu.ar/handle/10915/176192
work_keys_str_mv AT dalbiancopedroalejandro glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
AT riosgastongustavo glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
AT hasperuewaldo glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
AT stanchioscaragustin glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
AT ronchettifranco glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
AT quirogafacundomanuel glossfreeargentiniansignlanguagetranslationwithposebaseddeeplearningmodels
_version_ 1845116772112400384

Ejemplares similares