Robust and fast vowel recognition using optimum-path forest

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorPapa, João Paulo
dc.creatorMarana, Aparecido Nilceu
dc.creatorSpadotto, André A.
dc.creatorGuido, Rodrigo C.
dc.creatorFalcão, Alexandre X.
dc.date2014-05-27T11:24:50Z
dc.date2016-10-25T18:30:20Z
dc.date2014-05-27T11:24:50Z
dc.date2016-10-25T18:30:20Z
dc.date2010-11-08
dc.date.accessioned2017-04-06T01:43:30Z
dc.date.available2017-04-06T01:43:30Z
dc.identifierICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, p. 2190-2193.
dc.identifier1520-6149
dc.identifierhttp://hdl.handle.net/11449/71955
dc.identifierhttp://acervodigital.unesp.br/handle/11449/71955
dc.identifier10.1109/ICASSP.2010.5495695
dc.identifierWOS:000287096002042
dc.identifier2-s2.0-78049379155
dc.identifierhttp://dx.doi.org/10.1109/ICASSP.2010.5495695
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/892869
dc.descriptionThe 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.
dc.languageeng
dc.relationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectNeural networks
dc.subjectPattern recognition
dc.subjectSignal classification
dc.subjectSpeech recognition
dc.subjectArtificial neural networks
dc.subjectData sets
dc.subjectMachine-learning
dc.subjectPattern recognition techniques
dc.subjectProcessing systems
dc.subjectRealtime processing
dc.subjectSpoken languages
dc.subjectState-of-the-art system
dc.subjectTraining procedures
dc.subjectTraining time
dc.subjectVowel recognition
dc.subjectBiometrics
dc.subjectClassifiers
dc.subjectComputational linguistics
dc.subjectInformation theory
dc.subjectReal time systems
dc.subjectSignal processing
dc.subjectSpeech processing
dc.subjectSupport vector machines
dc.subjectTelecommunication equipment
dc.titleRobust and fast vowel recognition using optimum-path forest
dc.typeOtro


Este ítem pertenece a la siguiente institución