Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech

Detalhes bibliográficos
Autor(a) principal: De Almeida, Alex M. G. [UNESP]
Data de Publicação: 2021
Outros Autores: Guido, Rodrigo Capobianco [UNESP]
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/ISM52913.2021.00014
http://hdl.handle.net/11449/234169
Resumo: Although voice biometrics has been at the forefront of speech technologies, spoofing attacks have been one of the main issues responsible for avoiding its practical usage in commercial applications. Consequently, this article presents our proposed approach for building Knowledge-based wavelet filters, particularly dedicated to distinguish between genuine and spoofed speech. The main contribution of our strategy, particularly dedicated to identify replay attacks, is the acquisition of knowledge through the so called knowledge coefficients. Our results, obtained upon performing a set of experiments, indicate that the designed wavelet filters successfully classified hundreds of speech signals from our dataset, stimulating further research in this direction.
id UNSP_ce72387e1d5f7165a4d0fa754ac57362
oai_identifier_str oai:repositorio.unesp.br:11449/234169
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Knowledge-Based Wavelet Filters Prominently Detect Spoofed SpeechSpeaker VerificationWaveletAlthough voice biometrics has been at the forefront of speech technologies, spoofing attacks have been one of the main issues responsible for avoiding its practical usage in commercial applications. Consequently, this article presents our proposed approach for building Knowledge-based wavelet filters, particularly dedicated to distinguish between genuine and spoofed speech. The main contribution of our strategy, particularly dedicated to identify replay attacks, is the acquisition of knowledge through the so called knowledge coefficients. Our results, obtained upon performing a set of experiments, indicate that the designed wavelet filters successfully classified hundreds of speech signals from our dataset, stimulating further research in this direction.São Paulo State University São Jose Do Rio PretoSão Paulo State University São Jose Do Rio PretoUniversidade Estadual Paulista (UNESP)De Almeida, Alex M. G. [UNESP]Guido, Rodrigo Capobianco [UNESP]2022-05-01T13:57:27Z2022-05-01T13:57:27Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject35-38http://dx.doi.org/10.1109/ISM52913.2021.00014Proceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021, p. 35-38.http://hdl.handle.net/11449/23416910.1109/ISM52913.2021.000142-s2.0-85125016533Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021info:eu-repo/semantics/openAccess2022-05-01T13:57:27Zoai:repositorio.unesp.br:11449/234169Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-05-01T13:57:27Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
title Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
spellingShingle Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
De Almeida, Alex M. G. [UNESP]
Speaker Verification
Wavelet
title_short Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
title_full Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
title_fullStr Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
title_full_unstemmed Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
title_sort Knowledge-Based Wavelet Filters Prominently Detect Spoofed Speech
author De Almeida, Alex M. G. [UNESP]
author_facet De Almeida, Alex M. G. [UNESP]
Guido, Rodrigo Capobianco [UNESP]
author_role author
author2 Guido, Rodrigo Capobianco [UNESP]
author2_role author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
dc.contributor.author.fl_str_mv De Almeida, Alex M. G. [UNESP]
Guido, Rodrigo Capobianco [UNESP]
dc.subject.por.fl_str_mv Speaker Verification
Wavelet
topic Speaker Verification
Wavelet
description Although voice biometrics has been at the forefront of speech technologies, spoofing attacks have been one of the main issues responsible for avoiding its practical usage in commercial applications. Consequently, this article presents our proposed approach for building Knowledge-based wavelet filters, particularly dedicated to distinguish between genuine and spoofed speech. The main contribution of our strategy, particularly dedicated to identify replay attacks, is the acquisition of knowledge through the so called knowledge coefficients. Our results, obtained upon performing a set of experiments, indicate that the designed wavelet filters successfully classified hundreds of speech signals from our dataset, stimulating further research in this direction.
publishDate 2021
dc.date.none.fl_str_mv 2021-01-01
2022-05-01T13:57:27Z
2022-05-01T13:57:27Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/ISM52913.2021.00014
Proceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021, p. 35-38.
http://hdl.handle.net/11449/234169
10.1109/ISM52913.2021.00014
2-s2.0-85125016533
url http://dx.doi.org/10.1109/ISM52913.2021.00014
http://hdl.handle.net/11449/234169
identifier_str_mv Proceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021, p. 35-38.
10.1109/ISM52913.2021.00014
2-s2.0-85125016533
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Proceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 35-38
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1792961628244803584

Registros relacionados