The Art of Inquiry: Toward Robots that Infer Speech and Movement Characteristics

To improve user personalization of robots in social situations, robots can benefit from inferring information about the humans with whom they interact. Physical human behaviors and personality traits have previously been touted as possible sources of such information but often require complex processing or sensoring requirements. This paper investigates posing specific questions related to extrovert behaviors as an alternative source of this information. It aims to highlight significant relationships between questions aimed at behavioral reactions in specific scenarios and speech and movement attributes, obtained by a robot in a one-on-one social interaction. The paper used an experiment in which participants interacted with a robot through a non-scripted conversation. In it, the robot would gather information on the speech and movement characteristics, and estimated arousal/valence levels of the participant. The experiment was followed by a series of specific questions aimed at outlining the extroversion level of the participants. The results showed multiple significant but weak correlations $(\mathrm{p}\lt$.05) between the recorded attributes. These include correlations between the average determined valence and the average recorded velocity of speech, between the average answer reaction time and average answer length. The results also found correlations between arousal levels, average pause duration, and the answers recorded for individual questions of the questionnaire. The results suggest that introducing specific questions in human-robot interactions can potentially be used to decrease the processing and sensor demands of robots and offer user personalization using only a limited set of sensors.