Speech-to-speech translation humanoid robot in doctor's office

Abstract

This paper illustrates the implementation of a speech-to-speech translation humanoid robot in the domain of medical care. At this stage, the proposed system is a one-way translation that is designed to help English speaking patients describe their symptoms to Korean doctors or nurses. A humanoid robot is useful because it can be extended to reach out to people in need first and may substitute the role of human workers, unlike laptops or tablets. The system consists of three main parts - speech recognition, English-Korean translation, and Korean speech generation. It utilizes CMU Sphinx-4 as a speech recognition tool. English-Korean translation in this system is based on the rule-based translation. The success rate of the translation shows reliable results from an experiment with a closed scenario.