Embedded system based on multiprocessors to improve the control of a motorised wheelchair

The aim of this work is to implement an interesting application using small vocabulary word recognition processor and some smart sensors on a smart system. The adopted model is based on grouping a microcontroller and a DSP processor for speech enhancement with a new voice recognition module for isolated word and speaker dependent. The resulting design is used to control a wheelchair for a handicapped individuals based on a vocal command. In order to gain in time design, experiments have shown that the best way is to choose a speech recognition kit and to adapt it to the application. More over, A DSP processor is integrated in order to enhance the quality of speech signal by reducing noise and echo. The input of the system are a set of eight Arabic words used to control the movement of an electric wheelchair, a vector of information on the context given by a set of sensors and a joystick for security actions. The output is a corresponding command to the power module.