@article{PerugiaPaetzelPruesmannAlanenpaeaeetal.2021,
  author    = {Perugia, Giulia and Paetzel-Pr{\"u}smann, Maike and Alanenp{\"a}{\"a}, Madelene and Castellano, Ginevra},
  title     = {I can see it in your eyes},
  series = {Frontiers in robotics and AI},
  volume    = {8},
  journal   = {Frontiers in robotics and AI},
  publisher = {Frontiers Media},
  address   = {Lausanne},
  issn      = {2296-9144},
  doi       = {10.3389/frobt.2021.645956},
  pages     = {18},
  year      = {2021},
  abstract  = {Over the past years, extensive research has been dedicated to developing robust platforms and data-driven dialog models to support long-term human-robot interactions. However, little is known about how people's perception of robots and engagement with them develop over time and how these can be accurately assessed through implicit and continuous measurement techniques. In this paper, we explore this by involving participants in three interaction sessions with multiple days of zero exposure in between. Each session consists of a joint task with a robot as well as two short social chats with it before and after the task. We measure participants' gaze patterns with a wearable eye-tracker and gauge their perception of the robot and engagement with it and the joint task using questionnaires. Results disclose that aversion of gaze in a social chat is an indicator of a robot's uncanniness and that the more people gaze at the robot in a joint task, the worse they perform. In contrast with most HRI literature, our results show that gaze toward an object of shared attention, rather than gaze toward a robotic partner, is the most meaningful predictor of engagement in a joint task. Furthermore, the analyses of gaze patterns in repeated interactions disclose that people's mutual gaze in a social chat develops congruently with their perceptions of the robot over time. These are key findings for the HRI community as they entail that gaze behavior can be used as an implicit measure of people's perception of robots in a social chat and of their engagement and task performance in a joint task.},
  language  = {en}
}
@article{KuehneFischerZhou2020,
  author    = {K{\"u}hne, Katharina and Fischer, Martin H. and Zhou, Yuefang},
  title     = {The Human Takes It All},
  series = {Frontiers in Neurorobotics},
  volume    = {14},
  journal   = {Frontiers in Neurorobotics},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1662-5218},
  doi       = {10.3389/fnbot.2020.593732},
  pages     = {15},
  year      = {2020},
  abstract  = {Background: The increasing involvement of social robots in human lives raises the question as to how humans perceive social robots. Little is known about human perception of synthesized voices. Aim: To investigate which synthesized voice parameters predict the speaker's eeriness and voice likability; to determine if individual listener characteristics (e.g., personality, attitude toward robots, age) influence synthesized voice evaluations; and to explore which paralinguistic features subjectively distinguish humans from robots/artificial agents. Methods: 95 adults (62 females) listened to randomly presented audio-clips of three categories: synthesized (Watson, IBM), humanoid (robot Sophia, Hanson Robotics), and human voices (five clips/category). Voices were rated on intelligibility, prosody, trustworthiness, confidence, enthusiasm, pleasantness, human-likeness, likability, and naturalness. Speakers were rated on appeal, credibility, human-likeness, and eeriness. Participants' personality traits, attitudes to robots, and demographics were obtained. Results: The human voice and human speaker characteristics received reliably higher scores on all dimensions except for eeriness. Synthesized voice ratings were positively related to participants' agreeableness and neuroticism. Females rated synthesized voices more positively on most dimensions. Surprisingly, interest in social robots and attitudes toward robots played almost no role in voice evaluation. Contrary to the expectations of an uncanny valley, when the ratings of human-likeness for both the voice and the speaker characteristics were higher, they seemed less eerie to the participants. Moreover, when the speaker's voice was more humanlike, it was more liked by the participants. This latter point was only applicable to one of the synthesized voices. Finally, pleasantness and trustworthiness of the synthesized voice predicted the likability of the speaker's voice. Qualitative content analysis identified intonation, sound, emotion, and imageability/embodiment as diagnostic features. Discussion: Humans clearly prefer human voices, but manipulating diagnostic speech features might increase acceptance of synthesized voices and thereby support human-robot interaction. There is limited evidence that human-likeness of a voice is negatively linked to the perceived eeriness of the speaker.},
  language  = {en}
}