Speech quality classifier model based on DBN that considers atmospheric phenomena
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFLA |
Texto Completo: | http://repositorio.ufla.br/jspui/handle/1/42434 |
Resumo: | Current implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quality. Thus, the study of the transmitted signal quality at high frequencies is relevant to guaranty the user ́s quality of experience. In this research, the recommendations ITU-R P.838-3 and ITU-R P.676-11 are implemented in a network scenario, which are methodologies to estimate the signal degradations originated by rainfall and atmospheric gases, respectively. Thus, speech signals are encoded by the AMR-WB codec, transmitted and the perceptual speech quality is evaluated using the algorithm described in ITU-T Rec. P.863, mostly known as POLQA. The novelty of this work is to propose a non-intrusive speech quality classifier that considers atmospheric phenomena. This classifier is based on Deep Belief Networks (DBN) that uses Support Vector Machine (SVM) with radial basis function kernel (RBF-SVM) as classifier, to identify five predefined speech quality classes. Experimental Results show that the proposed speech quality classifier reached an accuracy between 92% and 95% for each quality class overcoming the results obtained by the sole non-intrusive standard described in ITU-T Recommendation P.563. Furthermore, subjective tests are carried out to validate the proposed classifier performance, and it reached an accuracy of 94.8%. |
id |
UFLA_300a33079b3ce8f7b90b1e14c5f77af1 |
---|---|
oai_identifier_str |
oai:localhost:1/42434 |
network_acronym_str |
UFLA |
network_name_str |
Repositório Institucional da UFLA |
repository_id_str |
|
spelling |
Speech quality classifier model based on DBN that considers atmospheric phenomenaWireless communicationsSpeech qualityAtmospheric phenomenaRainAtmospheric gasesComunicações sem fioVoz - QualidadeFenômenos atmosféricosChuvaGases atmosféricosCurrent implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quality. Thus, the study of the transmitted signal quality at high frequencies is relevant to guaranty the user ́s quality of experience. In this research, the recommendations ITU-R P.838-3 and ITU-R P.676-11 are implemented in a network scenario, which are methodologies to estimate the signal degradations originated by rainfall and atmospheric gases, respectively. Thus, speech signals are encoded by the AMR-WB codec, transmitted and the perceptual speech quality is evaluated using the algorithm described in ITU-T Rec. P.863, mostly known as POLQA. The novelty of this work is to propose a non-intrusive speech quality classifier that considers atmospheric phenomena. This classifier is based on Deep Belief Networks (DBN) that uses Support Vector Machine (SVM) with radial basis function kernel (RBF-SVM) as classifier, to identify five predefined speech quality classes. Experimental Results show that the proposed speech quality classifier reached an accuracy between 92% and 95% for each quality class overcoming the results obtained by the sole non-intrusive standard described in ITU-T Recommendation P.563. Furthermore, subjective tests are carried out to validate the proposed classifier performance, and it reached an accuracy of 94.8%.University of Split, FESB2020-08-14T19:00:03Z2020-08-14T19:00:03Z2020-03info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfSILVA, M. J. da et al. Speech quality classifier model based on DBN that considers atmospheric phenomena. Journal of Communications Software and Systems, Split, v. 16, n. 1, p. 75-84, Mar. 2020. DOI: http://dx.doi.org/10.24138/jcomss.v16i1.1033.http://repositorio.ufla.br/jspui/handle/1/42434Journal of Communications Software and Systemsreponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAhttp://creativecommons.org/licenses/by-nc/4.0/info:eu-repo/semantics/openAccessSilva, Marielle Jordane daCarrillo Melgarejo, DickRosa, Renata LopesZegarra Rodríguez, Demósteneseng2023-05-03T13:17:58Zoai:localhost:1/42434Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2023-05-03T13:17:58Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false |
dc.title.none.fl_str_mv |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
title |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
spellingShingle |
Speech quality classifier model based on DBN that considers atmospheric phenomena Silva, Marielle Jordane da Wireless communications Speech quality Atmospheric phenomena Rain Atmospheric gases Comunicações sem fio Voz - Qualidade Fenômenos atmosféricos Chuva Gases atmosféricos |
title_short |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
title_full |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
title_fullStr |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
title_full_unstemmed |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
title_sort |
Speech quality classifier model based on DBN that considers atmospheric phenomena |
author |
Silva, Marielle Jordane da |
author_facet |
Silva, Marielle Jordane da Carrillo Melgarejo, Dick Rosa, Renata Lopes Zegarra Rodríguez, Demóstenes |
author_role |
author |
author2 |
Carrillo Melgarejo, Dick Rosa, Renata Lopes Zegarra Rodríguez, Demóstenes |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Silva, Marielle Jordane da Carrillo Melgarejo, Dick Rosa, Renata Lopes Zegarra Rodríguez, Demóstenes |
dc.subject.por.fl_str_mv |
Wireless communications Speech quality Atmospheric phenomena Rain Atmospheric gases Comunicações sem fio Voz - Qualidade Fenômenos atmosféricos Chuva Gases atmosféricos |
topic |
Wireless communications Speech quality Atmospheric phenomena Rain Atmospheric gases Comunicações sem fio Voz - Qualidade Fenômenos atmosféricos Chuva Gases atmosféricos |
description |
Current implementations of 5G networks consider higher frequency range of operation than previous telecommunication networks, and it is possible to offer higher data rates for different applications. On the other hand, atmospheric phenomena could have a more negative impact on the transmission quality. Thus, the study of the transmitted signal quality at high frequencies is relevant to guaranty the user ́s quality of experience. In this research, the recommendations ITU-R P.838-3 and ITU-R P.676-11 are implemented in a network scenario, which are methodologies to estimate the signal degradations originated by rainfall and atmospheric gases, respectively. Thus, speech signals are encoded by the AMR-WB codec, transmitted and the perceptual speech quality is evaluated using the algorithm described in ITU-T Rec. P.863, mostly known as POLQA. The novelty of this work is to propose a non-intrusive speech quality classifier that considers atmospheric phenomena. This classifier is based on Deep Belief Networks (DBN) that uses Support Vector Machine (SVM) with radial basis function kernel (RBF-SVM) as classifier, to identify five predefined speech quality classes. Experimental Results show that the proposed speech quality classifier reached an accuracy between 92% and 95% for each quality class overcoming the results obtained by the sole non-intrusive standard described in ITU-T Recommendation P.563. Furthermore, subjective tests are carried out to validate the proposed classifier performance, and it reached an accuracy of 94.8%. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-08-14T19:00:03Z 2020-08-14T19:00:03Z 2020-03 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
SILVA, M. J. da et al. Speech quality classifier model based on DBN that considers atmospheric phenomena. Journal of Communications Software and Systems, Split, v. 16, n. 1, p. 75-84, Mar. 2020. DOI: http://dx.doi.org/10.24138/jcomss.v16i1.1033. http://repositorio.ufla.br/jspui/handle/1/42434 |
identifier_str_mv |
SILVA, M. J. da et al. Speech quality classifier model based on DBN that considers atmospheric phenomena. Journal of Communications Software and Systems, Split, v. 16, n. 1, p. 75-84, Mar. 2020. DOI: http://dx.doi.org/10.24138/jcomss.v16i1.1033. |
url |
http://repositorio.ufla.br/jspui/handle/1/42434 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/4.0/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
University of Split, FESB |
publisher.none.fl_str_mv |
University of Split, FESB |
dc.source.none.fl_str_mv |
Journal of Communications Software and Systems reponame:Repositório Institucional da UFLA instname:Universidade Federal de Lavras (UFLA) instacron:UFLA |
instname_str |
Universidade Federal de Lavras (UFLA) |
instacron_str |
UFLA |
institution |
UFLA |
reponame_str |
Repositório Institucional da UFLA |
collection |
Repositório Institucional da UFLA |
repository.name.fl_str_mv |
Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA) |
repository.mail.fl_str_mv |
nivaldo@ufla.br || repositorio.biblioteca@ufla.br |
_version_ |
1807835223987060736 |