Fast robot voice interface through optimum-path forest

dc.contributorUniversidade Estadual Paulista (Unesp)
dc.date.accessioned2014-05-27T11:27:04Z
dc.date.available2014-05-27T11:27:04Z
dc.date.created2014-05-27T11:27:04Z
dc.date.issued2012-10-01
dc.identifierINES 2012 - IEEE 16th International Conference on Intelligent Engineering Systems, Proceedings, p. 67-71.
dc.identifierhttp://hdl.handle.net/11449/73611
dc.identifier10.1109/INES.2012.6249804
dc.identifier2-s2.0-84866652350
dc.description.abstractVoice-based user interfaces have been actively pursued aiming to help individuals with motor impairments, providing natural interfaces to communicate with machines. In this work, we have introduced a recent machine learning technique named Optimum-Path Forest (OPF) for voice-based robot interface, which has been demonstrated to be similar to the state-of-the-art pattern recognition techniques, but much faster. Experiments were conducted against Support Vector Machines, Neural Networks and a Bayesian classifier to show the OPF robustness. The proposed architecture provides high accuracy rates allied with low computational times. © 2012 IEEE.
dc.languageeng
dc.relationINES 2012 - IEEE 16th International Conference on Intelligent Engineering Systems, Proceedings
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectAccuracy rate
dc.subjectBayesian classifier
dc.subjectComputational time
dc.subjectMachine learning techniques
dc.subjectMotor impairments
dc.subjectNatural interfaces
dc.subjectOptimum-path forests
dc.subjectPattern recognition techniques
dc.subjectProposed architectures
dc.subjectRobot interface
dc.subjectVoice interfaces
dc.subjectLearning systems
dc.subjectPattern recognition
dc.subjectUser interfaces
dc.subjectForestry
dc.subjectInterfaces
dc.subjectNetworks
dc.subjectOptimization
dc.subjectPatterns
dc.subjectRobots
dc.titleFast robot voice interface through optimum-path forest
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución