PHAST: Spoken document retrieval based on sequence alignment

This paper presents a new approach to spoken document information retrieval for spontaneous speech corpora. Classical approach to this problem is the use of an automatic speech recognizer (ASR) combined with standard information retrieval techniques, based on terms or n-grams. However, state-of-the-...

ver descrição completa

Detalhes bibliográficos
Autores: Comas Umbert, Pere Ramon, Turmo Borras, Jorge|||0000-0002-7521-1115
Formato: informe técnico
Fecha de publicación:2008
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/86459
Acesso em linha:https://hdl.handle.net/2117/86459
Access Level:acceso abierto
Palavra-chave:Information retrieval
Spoken document retrieval
Approximate matching
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_75e9c98135ca3a1318cdf4ce1bd4e40d
oai_identifier_str oai:upcommons.upc.edu:2117/86459
network_acronym_str ES
network_name_str España
repository_id_str
spelling PHAST: Spoken document retrieval based on sequence alignmentComas Umbert, Pere RamonTurmo Borras, Jorge|||0000-0002-7521-1115Information retrievalSpoken document retrievalApproximate matchingÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialThis paper presents a new approach to spoken document information retrieval for spontaneous speech corpora. Classical approach to this problem is the use of an automatic speech recognizer (ASR) combined with standard information retrieval techniques, based on terms or n-grams. However, state-of-the-art large vocabulary continuous ASRs produce transcripts of spontaneous speech with a word error rate of 25% or higher, which is a drawback for retrieval techniques based on terms or n-grams. In order to overcome such a limitation, our method is based on a sequence alignment algorithm drawn from the field of bioinformatics to search20082008-01-0120162016-05-02reporthttp://purl.org/coar/resource_type/c_93fcVoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/reportapplication/pdfhttps://hdl.handle.net/2117/86459reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/864592026-05-27T15:37:01Z
dc.title.none.fl_str_mv PHAST: Spoken document retrieval based on sequence alignment
title PHAST: Spoken document retrieval based on sequence alignment
spellingShingle PHAST: Spoken document retrieval based on sequence alignment
Comas Umbert, Pere Ramon
Information retrieval
Spoken document retrieval
Approximate matching
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short PHAST: Spoken document retrieval based on sequence alignment
title_full PHAST: Spoken document retrieval based on sequence alignment
title_fullStr PHAST: Spoken document retrieval based on sequence alignment
title_full_unstemmed PHAST: Spoken document retrieval based on sequence alignment
title_sort PHAST: Spoken document retrieval based on sequence alignment
dc.creator.none.fl_str_mv Comas Umbert, Pere Ramon
Turmo Borras, Jorge|||0000-0002-7521-1115
author Comas Umbert, Pere Ramon
author_facet Comas Umbert, Pere Ramon
Turmo Borras, Jorge|||0000-0002-7521-1115
author_role author
author2 Turmo Borras, Jorge|||0000-0002-7521-1115
author2_role author
dc.subject.none.fl_str_mv Information retrieval
Spoken document retrieval
Approximate matching
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Information retrieval
Spoken document retrieval
Approximate matching
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description This paper presents a new approach to spoken document information retrieval for spontaneous speech corpora. Classical approach to this problem is the use of an automatic speech recognizer (ASR) combined with standard information retrieval techniques, based on terms or n-grams. However, state-of-the-art large vocabulary continuous ASRs produce transcripts of spontaneous speech with a word error rate of 25% or higher, which is a drawback for retrieval techniques based on terms or n-grams. In order to overcome such a limitation, our method is based on a sequence alignment algorithm drawn from the field of bioinformatics to search
publishDate 2008
dc.date.none.fl_str_mv 2008
2008-01-01
2016
2016-05-02
dc.type.none.fl_str_mv report
http://purl.org/coar/resource_type/c_93fc
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/report
format report
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/86459
url https://hdl.handle.net/2117/86459
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
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411014177456128
score 15,301603

Registos relacionados