Development of Spoken Language Recognition System for Humanoid Robot
Abstract—“Pepper” robot has a variety of embedded abilities of interaction to communicate with humans such as Speech, Image, Detection, Gesture, and Tablet Service. Our research focused on interaction by speech recognition system of Pepper robot and analyzed its effectiveness. Since there are some limitations in built-in speech recognition system, we combine it with cloud-based speech recognition. The purpose of this research is to get the correct and reliable recognition of verbal speeches from users. Therefore, Speech API from Google Cloud service was used to implement more interactive behavior for Pepper robot.
Index Terms— Pepper Robot, Human Robot Interaction, Cloud-based Speech Recognition
Khaing Yee Mone, Yoshio Yamamoto
Tokai University, JAPAN
Cite: Khaing Yee Mone, Yoshio Yamamoto, "Development of Spoken Language Recognition System for Humanoid Robot," Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 57-62, Yangon (Rangoon), Myanmar (Burma), February 26-28, 2020.