MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension

[EN] This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politècnica de València for the Albayzín-RTVE 2020 Speech-to-Text Challenge, and includes an extension of the work consisting of building and evaluating equivalent systems u...

Descripción completa

Detalles Bibliográficos
Autores: Baquero-Arnal, Pau, Iranzo-Sánchez, Javier, Pérez-González de Martos, Alejandro Manuel, Jorge-Cano, Javier|||0000-0002-9279-6768, Giménez Pastor, Adrián, Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858, Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296, Civera Saiz, Jorge|||0000-0002-0963-0143, Sanchis Navarro, José Alberto|||0000-0002-2943-0990, Juan, Alfons|||0000-0002-9984-4072
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/194315
Acceso en línea:https://riunet.upv.es/handle/10251/194315
Access Level:acceso abierto
Palabra clave:Natural language processing
Automatic speech recognition
Streaming
LENGUAJES Y SISTEMAS INFORMATICOS
04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
10.- Reducir las desigualdades entre países y dentro de ellos
id ES_95531d4498ade04ffa33edcbb71e2cf7
oai_identifier_str oai:riunet.upv.es:10251/194315
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
title MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
spellingShingle MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
Baquero-Arnal, Pau
Natural language processing
Automatic speech recognition
Streaming
LENGUAJES Y SISTEMAS INFORMATICOS
04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
10.- Reducir las desigualdades entre países y dentro de ellos
title_short MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
title_full MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
title_fullStr MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
title_full_unstemmed MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
title_sort MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: Extension
dc.creator.none.fl_str_mv Baquero-Arnal, Pau
Iranzo-Sánchez, Javier
Pérez-González de Martos, Alejandro Manuel
Jorge-Cano, Javier|||0000-0002-9279-6768
Giménez Pastor, Adrián
Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
Civera Saiz, Jorge|||0000-0002-0963-0143
Sanchis Navarro, José Alberto|||0000-0002-2943-0990
Juan, Alfons|||0000-0002-9984-4072
author Baquero-Arnal, Pau
author_facet Baquero-Arnal, Pau
Iranzo-Sánchez, Javier
Pérez-González de Martos, Alejandro Manuel
Jorge-Cano, Javier|||0000-0002-9279-6768
Giménez Pastor, Adrián
Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
Civera Saiz, Jorge|||0000-0002-0963-0143
Sanchis Navarro, José Alberto|||0000-0002-2943-0990
Juan, Alfons|||0000-0002-9984-4072
author_role author
author2 Iranzo-Sánchez, Javier
Pérez-González de Martos, Alejandro Manuel
Jorge-Cano, Javier|||0000-0002-9279-6768
Giménez Pastor, Adrián
Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
Civera Saiz, Jorge|||0000-0002-0963-0143
Sanchis Navarro, José Alberto|||0000-0002-2943-0990
Juan, Alfons|||0000-0002-9984-4072
author2_role author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Sistemas Informáticos y Computación
Escuela Politécnica Superior de Alcoy
Escuela Técnica Superior de Ingeniería Informática
Escuela de Doctorado
Instituto Universitario Valenciano de Investigación en Inteligencia Artificial
Generalitat Valenciana
Ministerio de Educación
AGENCIA ESTATAL DE INVESTIGACION
European Regional Development Fund
European Commission
Universitat Politècnica de València
Ministerio de Ciencia, Innovación y Universidades
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Natural language processing
Automatic speech recognition
Streaming
LENGUAJES Y SISTEMAS INFORMATICOS
04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
10.- Reducir las desigualdades entre países y dentro de ellos
topic Natural language processing
Automatic speech recognition
Streaming
LENGUAJES Y SISTEMAS INFORMATICOS
04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
10.- Reducir las desigualdades entre países y dentro de ellos
description [EN] This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politècnica de València for the Albayzín-RTVE 2020 Speech-to-Text Challenge, and includes an extension of the work consisting of building and evaluating equivalent systems under the closed data conditions from the 2018 challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid ASR system using streaming one-pass decoding with a context window of 1.5 seconds. This system achieved 16.0% WER on the test-2020 set. We also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t which, following a similar configuration as the primary system with a smaller context window of 0.6 s, scored 16.9% WER points on the same test set, with a measured empirical latency of 0.81 ± 0.09 s (mean ± stdev). That is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. As an extension, the equivalent closed-condition systems obtained 23.3% WER and 23.5% WER, respectively. When evaluated with an unconstrained language model, we obtained 19.9% WER and 20.4% WER; i.e., not far behind the top-performing systems with only 5% of the full acoustic data and with the extra ability of being streaming-capable. Indeed, all of these streaming systems could be put into production environments for automatic captioning of live media streams.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/194315
url https://riunet.upv.es/handle/10251/194315
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 RTI2018-094879-B-I00 SUBTITULACION MULTILINGUE DE CLASES DE AULA Y SESIONES PLENARIAS
European Commission https://doi.org/10.13039/501100000780 Erasmus+ 2020-1-SI01-KA226-SCH-093604
European Commission https://doi.org/10.13039/501100000780 H2020 761758 X5gon: Cross Modal, Cross Cultural, Cross Lingual, Cross Domain, and Cross Site Global OER Network
MECYD MECYD Plan Estatal de investigación Científica y Técnica y de Innovación 2013-2016 FPU14%2F03981
European Commission https://doi.org/10.13039/501100000780 H2020 952215 Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization
Ministerio de Universidades MIU FPU18%2F04135 NOVEL CONTRIBUTIONS TO NEURAL SPEECH TRANSLATION
Generalitat Valenciana https://doi.org/10.13039/501100003359 PROMETEO%2F2019%2F111 CLASSROOM ACTIVITY RECOGNITION
Generalitat Valenciana https://doi.org/10.13039/501100003359 ACIF%2F2017%2F055
Universitat Politècnica de València https://doi.org/10.13039/501100004233 Programas de Apoyo a la I+D+i PAID-01-17 Ayudas para Contratos de Acceso de personal investigador doctor en estructuras de investigación de la Universitat Politècnica de València 2017- Subprograma 1
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/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
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI AG
publisher.none.fl_str_mv MDPI AG
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869413812814217216
spelling MLLP-VRAIN Spanish ASR Systems for the Albayzín-RTVE 2020 Speech-to-Text Challenge: ExtensionBaquero-Arnal, PauIranzo-Sánchez, JavierPérez-González de Martos, Alejandro ManuelJorge-Cano, Javier|||0000-0002-9279-6768Giménez Pastor, AdriánGarcés Díaz-Munío, Gonçal|||0000-0002-2594-5858Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296Civera Saiz, Jorge|||0000-0002-0963-0143Sanchis Navarro, José Alberto|||0000-0002-2943-0990Juan, Alfons|||0000-0002-9984-4072Natural language processingAutomatic speech recognitionStreamingLENGUAJES Y SISTEMAS INFORMATICOS04.- Garantizar una educación de calidad inclusiva y equitativa, y promover las oportunidades de aprendizaje permanente para todos09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación10.- Reducir las desigualdades entre países y dentro de ellos[EN] This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politècnica de València for the Albayzín-RTVE 2020 Speech-to-Text Challenge, and includes an extension of the work consisting of building and evaluating equivalent systems under the closed data conditions from the 2018 challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid ASR system using streaming one-pass decoding with a context window of 1.5 seconds. This system achieved 16.0% WER on the test-2020 set. We also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t which, following a similar configuration as the primary system with a smaller context window of 0.6 s, scored 16.9% WER points on the same test set, with a measured empirical latency of 0.81 ± 0.09 s (mean ± stdev). That is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. As an extension, the equivalent closed-condition systems obtained 23.3% WER and 23.5% WER, respectively. When evaluated with an unconstrained language model, we obtained 19.9% WER and 20.4% WER; i.e., not far behind the top-performing systems with only 5% of the full acoustic data and with the extra ability of being streaming-capable. Indeed, all of these streaming systems could be put into production environments for automatic captioning of live media streams.The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5Gon) and 952215 (TAILOR), and Erasmus+ Education programme under grant agreement no. 20-226-093604-SCH (EXPERT); the Government of Spain's grant RTI2018-094879-B-I00 (Multisub) funded by MCIN/AEI/10.13039/501100011033 & "ERDF A way of making Europe", and FPU scholarships FPU14/03981 and FPU18/04135; the Generalitat Valenciana's research project Classroom Activity Recognition (ref. PROMETEO/2019/111), and predoctoral research scholarship ACIF/2017/055; and the Universitat Politecnica de Valencia's PAID-01-17 R&D support programme.MDPI AGDepartamento de Sistemas Informáticos y ComputaciónEscuela Politécnica Superior de AlcoyEscuela Técnica Superior de Ingeniería InformáticaEscuela de DoctoradoInstituto Universitario Valenciano de Investigación en Inteligencia ArtificialGeneralitat ValencianaMinisterio de EducaciónAGENCIA ESTATAL DE INVESTIGACIONEuropean Regional Development FundEuropean CommissionUniversitat Politècnica de ValènciaMinisterio de Ciencia, Innovación y UniversidadesRepositorio Institucional de la Universitat Politècnica de València Riunet20222022-01-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://riunet.upv.es/handle/10251/194315reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 RTI2018-094879-B-I00 SUBTITULACION MULTILINGUE DE CLASES DE AULA Y SESIONES PLENARIASEuropean Commission https://doi.org/10.13039/501100000780 Erasmus+ 2020-1-SI01-KA226-SCH-093604European Commission https://doi.org/10.13039/501100000780 H2020 761758 X5gon: Cross Modal, Cross Cultural, Cross Lingual, Cross Domain, and Cross Site Global OER NetworkMECYD MECYD Plan Estatal de investigación Científica y Técnica y de Innovación 2013-2016 FPU14%2F03981European Commission https://doi.org/10.13039/501100000780 H2020 952215 Foundations of Trustworthy AI - Integrating Reasoning, Learning and OptimizationMinisterio de Universidades MIU FPU18%2F04135 NOVEL CONTRIBUTIONS TO NEURAL SPEECH TRANSLATIONGeneralitat Valenciana https://doi.org/10.13039/501100003359 PROMETEO%2F2019%2F111 CLASSROOM ACTIVITY RECOGNITIONGeneralitat Valenciana https://doi.org/10.13039/501100003359 ACIF%2F2017%2F055Universitat Politècnica de València https://doi.org/10.13039/501100004233 Programas de Apoyo a la I+D+i PAID-01-17 Ayudas para Contratos de Acceso de personal investigador doctor en estructuras de investigación de la Universitat Politècnica de València 2017- Subprograma 1open accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento (by)http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/1943152026-06-13T07:49:27Z
score 15.300719

Similares en LA Referencia