Optimal Approach to Speech Recognition with ROS

Among several ways of controlling a robotic system, voice control is one of the most sophisticated ways of issuing commands. Speech processing plays a key role in voice control. The main objective of this research work is to deliver a cost-efficient speech processing module and provide an audio response to the user. With the increase in usage of autonomous systems in recent times, users are looking towards cost efficient ways of Human-Robot Interaction. As ROS is an open source platform and the fact that many autonomous systems are being built over this platform has driven this research work. This research work was carried out to design one such module that can be integrated with the existing software stack of Robot Operating System easily.