New Anthropomorphic Talking Robot having Sensory Feedback Mechanism and Vocal Cords based on Human Biomechanical Structure

Abstract

We developed an anthropomorphic talking robot WT-5 (Waseda Talker No. 5) having a sensor feedback mechanism and novel vocal cords based on human biological structures. The sensory feedback is more important when we producing obstacle consonant sounds,, compared to the auditory feedback mechanism. We reproduce this mechanism by placing tactile sensors and a pressure sensor on the palate of a talking robot and reducing the error between the pressure of the human voice and the robot consonant production. The vocal cord model was constructed with a similar structure to the biological structure of the human vocal cords and vibrated like those of a human. In addition, using these mechanisms, WT-5 could produce voices closer to those of a human. And also realized continuous mimic speaking that includes consonant sounds.