This paper proposes a system whereby the human voice become a specific key to manipulate a robot, but nowhere a speech recognition module is used. In this system an android application is used to recognize human voice and is converted to text. This text is further processed and used to control robot. Keeping in mind the need of the day (requirements of the present day), our goal is to move towards making accessible to the manipulation of everyday objects to individuals with motor impairments. But voice (or speech) recognition module involves a high cost when it comes to practicality (reality). Using our system we perform several studies on control style variants for robots. Results show that it is indeed possible to learn to efficiently manipulate real world objects with only voice (human voice) as a control mechanism. Our results provide strong evidence that the further development of voice controlled robotics will be successful.

Full text: IJEIR_1513_Final.pdf