Prototype of wheelchair commanded by voice using HMM in a controlled environment

Prototype of wheelchair commanded by voice using HMM in a controlled environment

This article presents the development of a recognition system of speaker independent isolated words to command a wheelchair. Each word is encoded using techniques of Linear Prediction and Real Cepstrum, while the classification step is performed using Hidden Markov Models (HMM). From the results, co...

Descripción completa

Detalles Bibliográficos
Autores principales: Higuera-Martínez, Óscar Iván, Espitia-Flórez, Helberth Yesid, Méndez-Medina, Diego
Formato: Online
Lenguaje:spa
Publicado: Universidad Pedagógica y Tecnológica de Colombia - UPTC 2017
Materias:
hidden markov models
speech processing
linear prediction
cepstrum
modelos Ocultos de markov
procesamiento de voz
predicción lineal
Cepstrum
Acceso en línea:https://revistas.uptc.edu.co/index.php/ingenieria_sogamoso/article/view/5121
Descripción
Sumario:This article presents the development of a recognition system of speaker independent isolated words to command a wheelchair. Each word is encoded using techniques of Linear Prediction and Real Cepstrum, while the classification step is performed using Hidden Markov Models (HMM). From the results, commands are generated to a mobile system (wheelchair), which is led in a controlled environment.