Toward a hybrid technique to enhance vocal guiding system for a manipulator Arm”TR45”

In order to improve the rate of recognition for robots, a voice guiding system for a robot arm (manipulator) is designed as a part of a research project within the laboratory LAZA (ANNABA). The paradigm adopted is based on a combination of classical techniques used in automatic speech recognition system. To implement the approach on a real-time application, a personal computer interface was designed to control the movements of a four degree of freedom (DOF) didactic robot arm by transmitting the commands using wireless circuits. For a better rate of recognition, a pre-processing step for the speech signal based on Kalman filter is added. The voice command system for the robot arm is designed. The main parts of the robot are a microcontroller from microchip PIC16F84 and a radio frequency receiver module. The possibilities to control other parts of the automatic arm are investigated.