Fast robot voice interface through optimum-path forest

• Autor(a) principal: Nakamura, R. [UNESP]
• Data de Publicação: 2012
• Outros Autores: Pereira, L. [UNESP], Silva, D. [UNESP], Cardozo, P. [UNESP], Pereira, C. [UNESP], Ferasoli, H. [UNESP], Alves, S. [UNESP], Pires, R. [UNESP], Spadotto, A. [UNESP], Papa, J. [UNESP]
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1109/INES.2012.6249804; http://hdl.handle.net/11449/73611
• topic: Accuracy rate; Bayesian classifier; Computational time; Machine learning techniques; Motor impairments; Natural interfaces; Optimum-path forests; Pattern recognition techniques; Proposed architectures; Robot interface; Voice interfaces; Learning systems; Pattern recognition; User interfaces; Forestry; Interfaces; Networks; Optimization; Patterns; Robots

Voice-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.