Utterance Function for Companion Robot for Humans Watching Television

Abstract

In this work, we present the development of a on robot that can provide company to a person watching television (TV). To establish guidelines for developing the utterance function for the robot, we analyze the utterances of pairs of people watching TV together, which were then classified into eight categories. We observe that human-human dialogue while watching TV most often starts with “Disclosures” utterances that express one's own feelings. In addition, we found that utterances with high response rates could be classified as “Questions “Edifications,” and “Confirmations Based on this analysis, we implemented an utterance function in the robot under development that corresponds to “Disclosures” in relation to the TV program. The utterances generated by the robot are composed automatically by combining template sentences that include emotional words prepared from previous TV closed captions with keywords abstracted from the closed caption information of the program that the person is currently watching.