Authors : Mohamed Fezari , Mounir Bousbia-salah and Mouldi Bedda
Abstract: In this study we propose a simple approach to small vocabulary word recognition applied to control a wheelchair. The methodology adopted is based on hybrid techniques used in speech recognition which are zero crossing and extremes with dynamic time warping followed by a decision system based on independent methods test results. To test the approach on a real application, a PC interface was designed to control the movement of a wheelchair for a handicapped person by simple vocal messages. Tests showed that the decision system outputs follow a logic in line with the words uttered. The experiment aimed to find any problems for running tests in outdoor environments. Also, it was checked whether the basic commands used would be enough to control the vehicle. Some experiments are tested by actually running a powered-toy vehicle.
Mohamed Fezari , Mounir Bousbia-salah and Mouldi Bedda , 2006. Hybrid Technique to Enhance Voice Command for an Electric Wheelchair. Asian Journal of Information Technology, 5: 139-144.