Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation

The huge amount of information stored in audio and video repositories makes search on speech (SoS) a priority area nowadays. Within SoS, Query-by-Example Spoken Term Detection (QbE STD) aims to retrieve data from a speech repository given a spoken query. Research on this area is continuously fostere...

ver descrição completa

Detalhes bibliográficos
Autores: Tejedor, Javier, López Otero, Paula, Docio Fernandez, Laura, Rodríguez Fuentes, Luis Javier, Torre Toledano, Doroteo, Moreno Sandoval, Antonio, Peñagarikano, Mikel
Formato: artículo
Fecha de publicación:2019
País:España
Recursos:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/716422
Acesso em linha:http://hdl.handle.net/10486/716422
https://dx.doi.org/10.1186/s13636-019-0156-x
Access Level:acceso abierto
Palavra-chave:International evaluation
Search on speech
Spanish language
Query-by-example spoken term detection
Telecomunicaciones
id ES_29323f4c8a2229e5b36b34bd8e55e9a3
oai_identifier_str oai:repositorio.uam.es:10486/716422
network_acronym_str ES
network_name_str España
repository_id_str
spelling Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluationTejedor, JavierLópez Otero, PaulaDocio Fernandez, LauraRodríguez Fuentes, Luis JavierTorre Toledano, DoroteoMoreno Sandoval, AntonioPeñagarikano, MikelInternational evaluationSearch on speechSpanish languageQuery-by-example spoken term detectionTelecomunicacionesThe huge amount of information stored in audio and video repositories makes search on speech (SoS) a priority area nowadays. Within SoS, Query-by-Example Spoken Term Detection (QbE STD) aims to retrieve data from a speech repository given a spoken query. Research on this area is continuously fostered with the organization of QbE STD evaluations. This paper presents a multi-domain internationally open evaluation for QbE STD in Spanish. The evaluation aims at retrieving the speech files that contain the queries, providing their start and end times, and a score that reflects the confidence given to the detection. Three different Spanish speech databases that encompass different domains have been employed in the evaluation: MAVIR database, which comprises a set of talks from workshops; RTVE database, which includes broadcast television (TV) shows; and COREMAH database, which contains 2-people spontaneous speech conversations about different topics. The evaluation has been designed carefully so that several analyses of the main results can be carried out. We present the evaluation itself, the three databases, the evaluation metrics, the systems submitted to the evaluation, the results, and the detailed post-evaluation analyses based on some query properties (within-vocabulary/out-of-vocabulary queries, single-word/multi-word queries, and native/foreign queries). Fusion results of the primary systems submitted to the evaluation are also presented. Three different teams took part in the evaluation, and ten different systems were submitted. The results suggest that the QbE STD task is still in progress, and the performance of these systems is highly sensitive to changes in the data domain. Nevertheless, QbE STD strategies are able to outperform text-based STD in unseen data domainsThis work has received financial support from “Ministerio de Economía y Competitividad” of the Government of Spain, Xunta de Galicia - “Consellería de Cultura, Educación e Ordenación Universitaria”, the European Regional Development Fund through the 2016-2019 accreditations ED431G/01 (“Centro singular de investigación de Galicia”) and ED431G/04 (“Agrupación estratéxica consolidada”), the UPV/EHU under grant GIU16/68, the project “DSSL: Redes Profundas y Modelos de Subespacios para Detección y Seguimiento de Locutor, Idioma y Enfermedades Degenerativas a partir de la Voz” (TEC2015-68172-C2-1-P, MINECO/FEDER), the project “DSForSec: Deep Speech for Forensics and Security” funded by the Ministry of Science, Innovation and Universities and FEDER (RTI2018-098091-B-I00), and the Cátedra UNIZAR-RTVEDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica SuperiorAudias - Audio, Data Intelligence and Speech20192019-07-19research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/716422https://dx.doi.org/10.1186/s13636-019-0156-xreponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/7164222026-06-23T12:46:27Z
dc.title.none.fl_str_mv Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
title Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
spellingShingle Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
Tejedor, Javier
International evaluation
Search on speech
Spanish language
Query-by-example spoken term detection
Telecomunicaciones
title_short Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
title_full Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
title_fullStr Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
title_full_unstemmed Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
title_sort Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-example spoken term detection evaluation
dc.creator.none.fl_str_mv Tejedor, Javier
López Otero, Paula
Docio Fernandez, Laura
Rodríguez Fuentes, Luis Javier
Torre Toledano, Doroteo
Moreno Sandoval, Antonio
Peñagarikano, Mikel
author Tejedor, Javier
author_facet Tejedor, Javier
López Otero, Paula
Docio Fernandez, Laura
Rodríguez Fuentes, Luis Javier
Torre Toledano, Doroteo
Moreno Sandoval, Antonio
Peñagarikano, Mikel
author_role author
author2 López Otero, Paula
Docio Fernandez, Laura
Rodríguez Fuentes, Luis Javier
Torre Toledano, Doroteo
Moreno Sandoval, Antonio
Peñagarikano, Mikel
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
Audias - Audio, Data Intelligence and Speech
dc.subject.none.fl_str_mv International evaluation
Search on speech
Spanish language
Query-by-example spoken term detection
Telecomunicaciones
topic International evaluation
Search on speech
Spanish language
Query-by-example spoken term detection
Telecomunicaciones
description The huge amount of information stored in audio and video repositories makes search on speech (SoS) a priority area nowadays. Within SoS, Query-by-Example Spoken Term Detection (QbE STD) aims to retrieve data from a speech repository given a spoken query. Research on this area is continuously fostered with the organization of QbE STD evaluations. This paper presents a multi-domain internationally open evaluation for QbE STD in Spanish. The evaluation aims at retrieving the speech files that contain the queries, providing their start and end times, and a score that reflects the confidence given to the detection. Three different Spanish speech databases that encompass different domains have been employed in the evaluation: MAVIR database, which comprises a set of talks from workshops; RTVE database, which includes broadcast television (TV) shows; and COREMAH database, which contains 2-people spontaneous speech conversations about different topics. The evaluation has been designed carefully so that several analyses of the main results can be carried out. We present the evaluation itself, the three databases, the evaluation metrics, the systems submitted to the evaluation, the results, and the detailed post-evaluation analyses based on some query properties (within-vocabulary/out-of-vocabulary queries, single-word/multi-word queries, and native/foreign queries). Fusion results of the primary systems submitted to the evaluation are also presented. Three different teams took part in the evaluation, and ten different systems were submitted. The results suggest that the QbE STD task is still in progress, and the performance of these systems is highly sensitive to changes in the data domain. Nevertheless, QbE STD strategies are able to outperform text-based STD in unseen data domains
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-07-19
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
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 http://hdl.handle.net/10486/716422
https://dx.doi.org/10.1186/s13636-019-0156-x
url http://hdl.handle.net/10486/716422
https://dx.doi.org/10.1186/s13636-019-0156-x
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
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
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404989780131840
score 15.228081

Registos relacionados