HMM-based phoneme speech recognition system for control and command of
In recent years integration of Human-Robot interaction with speech
recognition has gained a lot of pace in the manufacturing industries.
Undoubtedly, this bridges the large gap created between the operator and
robot by communication’s point of view. Although there are numerous ways
in which communication can be established between a human operator and
the robot-like, controlling with a teaching pendant, or a joystick.
Currently, the robots are controlled semi-autonomously by means of a
computer. However, speech and touch  are natural ways of
communication in humans, where speech recognition, being the best, is
heavily researched technology. In this study, we aim at developing a
stable and robust speech recognition system to allow humans to
communicate with machines (Robotic-arm) in a seamless manner. This paper
intends to investigate the potential of the Linear Predictive coding
technique to develop a stable and robust HMM-based phoneme speech
recognition system for robotics applications. Our system is divided into
three segments: a microphone array, a voice module, and a 3-DOF robotic
arm (Figure 1). To validate our approach, we have performed tests with
simple and complex sentences for various robotics activities like
manipulating a cube and pick and place tasks. Moreover, we also analyzed
the test results to rectify problems like accuracy, recognition score,
etc. Also the paper briefly enumerates the future prospects and
applications of our approach.