Analysis of Long-Term and Large-Scale Experiments on Robot Dialogues Using a Cloud Robotics Platform

摘要: To build conversational robots, roboticists are required to have deep knowledge of both robotics and spoken dialogue systems. Unlike using stand-alone speech recognition/ synthesis toolkits, a cloud platform for human-robot communication enables high-quality recognition that is optimized interactions. This challenging because we need wide variety functionalities ranging from stable multilingual engines. From this background, constructed rospeex [1], which dialogues with robots. Over 20,000 unique users used in the two years since it was launched. In paper, propose method reduce response time rospeex; analyze its effectiveness. We also server logs collected.