Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge

The vast amount of information stored in audio repositories makes necessary the development of efficient and automatic methods to search on audio content. In that direction, search on speech (SoS) has received much attention in the last decades. To motivate the development of automatic systems, ALBA...

Descripción completa

Detalles Bibliográficos
Autores: Tejedor, Javier, Torre Toledano, Doroteo
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/716421
Acceso en línea:http://hdl.handle.net/10486/716421
https://dx.doi.org/10.1186/s13636-024-00334-w
Access Level:acceso abierto
Palabra clave:ALBAYZIN evaluations
Search on speech
Spoken term detection
Whisper
Telecomunicaciones
id ES_10fc513ff46f489fb2cd2fe2fa0c0e66
oai_identifier_str oai:repositorio.uam.es:10486/716421
network_acronym_str ES
network_name_str España
repository_id_str
spelling Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challengeTejedor, JavierTorre Toledano, DoroteoALBAYZIN evaluationsSearch on speechSpoken term detectionWhisperTelecomunicacionesThe vast amount of information stored in audio repositories makes necessary the development of efficient and automatic methods to search on audio content. In that direction, search on speech (SoS) has received much attention in the last decades. To motivate the development of automatic systems, ALBAYZIN evaluations include a search on speech challenge since 2012. This challenge releases several databases that cover different acoustic domains (i.e., spontaneous speech from TV shows, conference talks, parliament sessions, to name a few) aiming to build automatic systems that retrieve a set of terms from those databases. This paper presents a baseline system based on the Whisper automatic speech recognizer for the spoken term detection task in the search on speech challenge held in 2022 within the ALBAYZIN evaluations. This baseline system will be released with this publication and will be given to participants in the upcoming SoS ALBAYZIN evaluation in 2024. Additionally, several analyses based on some term properties (i.e., in-language and foreign terms, and single-word and multi-word terms) are carried out to show the Whisper capability at retrieving terms that convey specific properties. Although the results obtained for some databases are far from being perfect (e.g., for broadcast news domain), this Whisper-based approach has obtained the best results on the challenge databases so far so that it presents a strong baseline system for the upcoming challenge, encouraging participants to improve itFunded by projects RTI2018-098091-B-I00 and PID2021-125943OB-I00 (Spanish Ministry of Science and Innovation and ERDF)SpringerOpenDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica SuperiorAudias - Audio, Data Intelligence and Speech20242024-02-29research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/716421https://dx.doi.org/10.1186/s13636-024-00334-wreponame: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:10486/7164212026-06-23T12:46:27Z
dc.title.none.fl_str_mv Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
title Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
spellingShingle Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
Tejedor, Javier
ALBAYZIN evaluations
Search on speech
Spoken term detection
Whisper
Telecomunicaciones
title_short Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
title_full Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
title_fullStr Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
title_full_unstemmed Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
title_sort Whisper-based spoken term detection systems for search on speech ALBAYZIN evaluation challenge
dc.creator.none.fl_str_mv Tejedor, Javier
Torre Toledano, Doroteo
author Tejedor, Javier
author_facet Tejedor, Javier
Torre Toledano, Doroteo
author_role author
author2 Torre Toledano, Doroteo
author2_role 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 ALBAYZIN evaluations
Search on speech
Spoken term detection
Whisper
Telecomunicaciones
topic ALBAYZIN evaluations
Search on speech
Spoken term detection
Whisper
Telecomunicaciones
description The vast amount of information stored in audio repositories makes necessary the development of efficient and automatic methods to search on audio content. In that direction, search on speech (SoS) has received much attention in the last decades. To motivate the development of automatic systems, ALBAYZIN evaluations include a search on speech challenge since 2012. This challenge releases several databases that cover different acoustic domains (i.e., spontaneous speech from TV shows, conference talks, parliament sessions, to name a few) aiming to build automatic systems that retrieve a set of terms from those databases. This paper presents a baseline system based on the Whisper automatic speech recognizer for the spoken term detection task in the search on speech challenge held in 2022 within the ALBAYZIN evaluations. This baseline system will be released with this publication and will be given to participants in the upcoming SoS ALBAYZIN evaluation in 2024. Additionally, several analyses based on some term properties (i.e., in-language and foreign terms, and single-word and multi-word terms) are carried out to show the Whisper capability at retrieving terms that convey specific properties. Although the results obtained for some databases are far from being perfect (e.g., for broadcast news domain), this Whisper-based approach has obtained the best results on the challenge databases so far so that it presents a strong baseline system for the upcoming challenge, encouraging participants to improve it
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-02-29
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/10486/716421
https://dx.doi.org/10.1186/s13636-024-00334-w
url http://hdl.handle.net/10486/716421
https://dx.doi.org/10.1186/s13636-024-00334-w
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.publisher.none.fl_str_mv SpringerOpen
publisher.none.fl_str_mv SpringerOpen
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_ 1869403540742471680
score 15,81155

Similares en LA Referencia