Towards a Real-time Measure of the Perception of Anthropomorphism in Human-robot Interaction

How human-like do conversational robots need to look to enable long-term human-robot conversation? One essential aspect of long-term interaction is a human's ability to adapt to the varying degrees of a conversational partner's engagement and emotions. Prosodically, this can be achieved through (dis)entrainment. While speech-synthesis has been a limiting factor for many years, restrictions in this regard are increasingly mitigated. These advancements now emphasise the importance of studying the effect of robot embodiment on human entrainment. In this study, we conducted a between-subjects online human-robot interaction experiment in an educational use-case scenario where a tutor was either embodied through a human or a robot face. 43 English-speaking participants took part in the study for whom we analysed the degree of acoustic-prosodic entrainment to the human or robot face, respectively. We found that the degree of subjective and objective perception of anthropomorphism positively correlates with acoustic-prosodic entrainment.

[1]  A. Stolcke,et al.  A Study of Multimodal Addressee Detection in Human-Human-Computer Interaction , 2015, IEEE Transactions on Multimedia.

[2]  Jonathan Levy,et al.  Oxytocin selectively modulates brain response to stimuli probing social synchrony , 2016, NeuroImage.

[3]  Julia Hirschberg,et al.  Acoustic-Prosodic Entrainment and Social Behavior , 2012, NAACL.

[4]  Andreas Stolcke,et al.  Addressee detection for dialog systems using temporal and spectral dimensions of speaking style , 2013, INTERSPEECH.

[5]  Antske Fokkens,et al.  A Research Agenda for Hybrid Intelligence: Augmenting Human Intellect With Collaborative, Adaptive, Responsible, and Explainable Artificial Intelligence , 2020, Computer.

[6]  Gabriel Skantze,et al.  Furhat: A Back-Projected Human-Like Robot Head for Multiparty Human-Machine Interaction , 2011, COST 2102 Training School.

[7]  Heather Pon-Barry,et al.  Effects of voice-adaptation and social dialogue on perceptions of a robotic learning companion , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[8]  Cynthia Breazeal.  Regulation and Entrainment in Human-Robot Interaction , 2000, ISER.

[9]  Nick Campbell,et al.  Measuring Dynamics of Mimicry by Means of Prosodic Cues in Conversational Speech , 2011, ICPhS.

[10]  G. Rizzolatti,et al.  The mirror-neuron system. , 2004, Annual review of neuroscience.

[11]  Dana Kulic,et al.  Measurement Instruments for the Anthropomorphism, Animacy, Likeability, Perceived Intelligence, and Perceived Safety of Robots , 2009, Int. J. Soc. Robotics.

[12]  Julia Hirschberg,et al.  Implementing Acoustic-Prosodic Entrainment in a Conversational Avatar , 2016, INTERSPEECH.

[13]  Cynthia Breazeal,et al.  A Comparison of Children Learning New Words from Robots , Tablets , & People , 2015 .

[14]  Jesse Thomason,et al.  Prosodic Entrainment and Tutoring Dialogue Success , 2013, AIED.

[15]  Dilek Z. Hakkani-Tür,et al.  Learning When to Listen: Detecting System-Addressed Speech in Human-Human-Computer Dialog , 2012, INTERSPEECH.

[16]  Justin Scott Giboney,et al.  The impact of chatbot conversational skill on engagement and perceived humanness , 2020, J. Manag. Inf. Syst..

[17]  Matthew Gombolay,et al.  Effects of Anthropomorphism and Accountability on Trust in Human Robot Interaction , 2020, 2020 15th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[18]  Jordi Luque,et al.  A unifying framework for modeling acoustic/prosodic entrainment: definition and evaluation on two large corpora , 2020, SIGDIAL.

[19]  Uwe D. Reichel,et al.  Prosodic entrainment in dialog acts , 2018, ArXiv.

[20]  Heather Pon-Barry,et al.  Acoustic-Prosodic Entrainment and Rapport in Collaborative Learning Dialogues , 2014, MLA@ICMI.

[21]  Bart de Boer,et al.  Introducing Parselmouth: A Python interface to Praat , 2018, J. Phonetics.

[22]  Jill Fain Lehman,et al.  Creating Prosodic Synchrony for a Robot Co-Player in a Speech-Controlled Game for Children , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[23]  Cynthia Breazeal,et al.  Regulation and Entrainment in Human—Robot Interaction , 2000, Int. J. Robotics Res..

[24]  John Sweller,et al.  The Mirror Neuron System and Observational Learning: Implications for the Effectiveness of Dynamic Visualizations , 2009 .

[25]  L. Tickle-Degnen,et al.  The Nature of Rapport and Its Nonverbal Correlates , 1990 .

[26]  L. Nygaard,et al.  Vocal alignment to native and non-native speakers of English. , 2018, The Journal of the Acoustical Society of America.

[27]  Oliver Niebuhr,et al.  Influence of Robot Gender and Speaker Gender on Prosodic Entrainment in HRI , 2017 .

[28]  Samuel S. Monfort,et al.  Almost human: Anthropomorphism increases trust resilience in cognitive agents. , 2016, Journal of experimental psychology. Applied.

[29]  Sonya S. Kwak,et al.  The Effect of Robot Appearance Types on Motivating Donation , 2014, 2014 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[30]  Mark Liberman,et al.  TOWARDS AN INTEGRATED UNDERSTANDING OF SPEECH OVERLAPS IN CONVERSATION , 2007 .