Robust and fast vowel recognition using optimum-path forest

Detalhes bibliográficos
Autor(a) principal: Papa, João Paulo [UNESP]
Data de Publicação: 2010
Outros Autores: Marana, Aparecido Nilceu [UNESP], Spadotto, André A., Guido, Rodrigo C., Falcão, Alexandre X.
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/ICASSP.2010.5495695
http://hdl.handle.net/11449/71955
Resumo: The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.
id UNSP_cd295c2fa0c6410dec213d4cc8d37c35
oai_identifier_str oai:repositorio.unesp.br:11449/71955
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Robust and fast vowel recognition using optimum-path forestNeural networksPattern recognitionSignal classificationSpeech recognitionArtificial neural networksData setsMachine-learningPattern recognition techniquesProcessing systemsRealtime processingSpoken languagesState-of-the-art systemTraining proceduresTraining timeVowel recognitionBiometricsClassifiersComputational linguisticsInformation theoryReal time systemsSignal processingSpeech processingSupport vector machinesTelecommunication equipmentThe applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.São Paulo State University Computer Science DepartmentUniversity of São Paulo Physics Institute of São CarlosUniversity of Campinas Institute of ComputingSão Paulo State University Computer Science DepartmentUniversidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Universidade Estadual de Campinas (UNICAMP)Papa, João Paulo [UNESP]Marana, Aparecido Nilceu [UNESP]Spadotto, André A.Guido, Rodrigo C.Falcão, Alexandre X.2014-05-27T11:24:50Z2014-05-27T11:24:50Z2010-11-08info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject2190-2193http://dx.doi.org/10.1109/ICASSP.2010.5495695ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, p. 2190-2193.1520-6149http://hdl.handle.net/11449/7195510.1109/ICASSP.2010.5495695WOS:0002870960020422-s2.0-780493791559039182932747194602771375094268965420862268080670000-0002-0924-8024Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedingsinfo:eu-repo/semantics/openAccess2024-04-23T16:11:33Zoai:repositorio.unesp.br:11449/71955Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T21:37:31.332369Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Robust and fast vowel recognition using optimum-path forest
title Robust and fast vowel recognition using optimum-path forest
spellingShingle Robust and fast vowel recognition using optimum-path forest
Papa, João Paulo [UNESP]
Neural networks
Pattern recognition
Signal classification
Speech recognition
Artificial neural networks
Data sets
Machine-learning
Pattern recognition techniques
Processing systems
Realtime processing
Spoken languages
State-of-the-art system
Training procedures
Training time
Vowel recognition
Biometrics
Classifiers
Computational linguistics
Information theory
Real time systems
Signal processing
Speech processing
Support vector machines
Telecommunication equipment
title_short Robust and fast vowel recognition using optimum-path forest
title_full Robust and fast vowel recognition using optimum-path forest
title_fullStr Robust and fast vowel recognition using optimum-path forest
title_full_unstemmed Robust and fast vowel recognition using optimum-path forest
title_sort Robust and fast vowel recognition using optimum-path forest
author Papa, João Paulo [UNESP]
author_facet Papa, João Paulo [UNESP]
Marana, Aparecido Nilceu [UNESP]
Spadotto, André A.
Guido, Rodrigo C.
Falcão, Alexandre X.
author_role author
author2 Marana, Aparecido Nilceu [UNESP]
Spadotto, André A.
Guido, Rodrigo C.
Falcão, Alexandre X.
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Universidade de São Paulo (USP)
Universidade Estadual de Campinas (UNICAMP)
dc.contributor.author.fl_str_mv Papa, João Paulo [UNESP]
Marana, Aparecido Nilceu [UNESP]
Spadotto, André A.
Guido, Rodrigo C.
Falcão, Alexandre X.
dc.subject.por.fl_str_mv Neural networks
Pattern recognition
Signal classification
Speech recognition
Artificial neural networks
Data sets
Machine-learning
Pattern recognition techniques
Processing systems
Realtime processing
Spoken languages
State-of-the-art system
Training procedures
Training time
Vowel recognition
Biometrics
Classifiers
Computational linguistics
Information theory
Real time systems
Signal processing
Speech processing
Support vector machines
Telecommunication equipment
topic Neural networks
Pattern recognition
Signal classification
Speech recognition
Artificial neural networks
Data sets
Machine-learning
Pattern recognition techniques
Processing systems
Realtime processing
Spoken languages
State-of-the-art system
Training procedures
Training time
Vowel recognition
Biometrics
Classifiers
Computational linguistics
Information theory
Real time systems
Signal processing
Speech processing
Support vector machines
Telecommunication equipment
description The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.
publishDate 2010
dc.date.none.fl_str_mv 2010-11-08
2014-05-27T11:24:50Z
2014-05-27T11:24:50Z
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/ICASSP.2010.5495695
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, p. 2190-2193.
1520-6149
http://hdl.handle.net/11449/71955
10.1109/ICASSP.2010.5495695
WOS:000287096002042
2-s2.0-78049379155
9039182932747194
6027713750942689
6542086226808067
0000-0002-0924-8024
url http://dx.doi.org/10.1109/ICASSP.2010.5495695
http://hdl.handle.net/11449/71955
identifier_str_mv ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, p. 2190-2193.
1520-6149
10.1109/ICASSP.2010.5495695
WOS:000287096002042
2-s2.0-78049379155
9039182932747194
6027713750942689
6542086226808067
0000-0002-0924-8024
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 2190-2193
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_ 1808129342444666880