Ilaria Torre

Ilaria Torre
KTH Royal Institute of Technology | KTH · Robotics Perception and Learning

PhD

About

34
Publications
11,363
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
215
Citations
Introduction
Ilaria Torre currently works as a postdoctoral researcher in the Division of Robotics, Perception and Learning, KTH. Ilaria does research in Human-Machine Interaction, looking particularly at how different speech/ behaviour/ emotion cues affect cooperation and trust in human-machine teams.
Education
April 2014 - August 2017
University of Plymouth, CogNovo
Field of study
  • Psychology

Publications

Publications (34)
Conference Paper
Full-text available
Societies rely on trustworthy communication in order to function, and the need for trust clearly extends to human-machine communication. Therefore, it is essential to design machines to elicit trust, so as to make interactions with them acceptable and successful. However, while there is a substantial literature on first impressions of trustworthine...
Conference Paper
Full-text available
It is well established that a robot's visual appearance plays a significant role in how it is perceived. Considerable time and resources are usually dedicated to help ensure that the visual aesthetics of social robots are pleasing to users and helps facilitate clear communication. However, relatively little consideration is given to how the voice o...
Article
While it is clear that artificial agents that are able to express emotions increase trust in Human–Machine Interaction, most studies looking at this effect concentrated on the expression of emotions through the visual channel, e.g. facial expressions. However, emotions can be expressed in the vocal channel too, yet the relationship between trust an...
Conference Paper
Accents are vocal features that immediately tell a listener whether a speaker comes from their same place, i.e. whether they share a social group. This in-groupness is important, as people tend to prefer interacting with others who belong to their same groups. Accents also evoke attitudinal responses based on their supposed prestigious status. Thes...
Article
Emotional expressivity is essential for human interactions, informing both perception and decision-making. Here, we examine whether creating an audio-visual emotional channel mismatch influences decision-making in a cooperative task with a virtual character. We created a virtual character that was either congruent in its emotional expression (smili...
Conference Paper
Multisensory integration influences emotional per- ception, as the McGurk effect demonstrates for the communi- cation between humans. Human physiology implicitly links the production of visual features with other modes like the audio channel: Face muscles responsible for a smiling face also stretch the vocal cords that results in a characteristic s...
Conference Paper
Artificial agents’ smiling behaviour is likely to influence their likeability and the quality of user experience. While studies of human interaction highlight the importance of smile dynamics, this feature is often lacking in artificial agents, presenting a design opportunity. We developed a virtual motivational therapist with four smiling behaviou...
Preprint
In this paper we present a pilot study which investigates how non-verbal behavior affects social influence in social robots. We also present a modular system which is capable of controlling the non-verbal behavior based on the interlocutor's facial gestures (head movements and facial expressions) in real time, and a study investigating whether thre...
Article
Full-text available
When presented with voices, we make rapid, automatic judgements of social traits such as trustworthiness – and such judgements are highly consistent across listeners. However, it remains unclear whether voice-based first impressions actually influence behaviour towards a voice’s owner, and – if they do – whether and how they interact over time with...
Conference Paper
Full-text available
Driving styles play a major role in the acceptance and use of autonomous vehicles. Yet, existing motion planning techniques can often only incorporate simple driving styles that are modeled by the developers of the planner and not tailored to the passenger. We present a new approach to encode human driving styles through the use of signal tempora...
Conference Paper
Full-text available
Perceived robot identity has not been discussed thoroughly in Human-Robot Interaction. In particular, very few works have explored how humans tend to perceive robots that migrate through a variety of media and devices. In this paper, we discuss some of the open challenges for artificial robot identity stemming from the robotic features of voice, em...
Conference Paper
Conducting user studies is a crucial component in many scientific fields. While some studies require participants to be physically present, other studies can be conducted both physically (e.g. in-lab) and online (e.g. via crowdsourcing). Inviting participants to the lab can be a time-consuming and logistically difficult endeavor, not to mention tha...
Conference Paper
Social robots have a recognizable physical appearance, a distinct voice, and interact with users in specific contexts. Previous research has suggested a ‘matching hypothesis’, which seeks to rationalise how people judge a robot’s appropriateness for a task by its appearance. Other research has extended this to cover combinations of robot voices and...
Chapter
Trust is fundamental for successful human interactions. As robots become increasingly active in human society, it is essential to determine what characteristics of robots influence trust in human–robot interaction, in order to design robots with which people feel comfortable interacting. Many interactions are vocal by nature, yet the vocal correlat...
Preprint
Conducting user studies is a crucial component in many scientific fields. While some studies require participants to be physically present, other studies can be conducted both physically (e.g. in-lab) and online (e.g. via crowdsourcing). Inviting participants to the lab can be a time-consuming and logistically difficult endeavor, not to mention tha...
Chapter
Creative destruction’ is a macroeconomic term describing a cycle of renewal. Triggered by innovation, a novel and useful solution enters the market and subsequently replaces existing participation. Creative destruction has been described as the drive of capitalism, where forceful and rapid renewal replaces existing entities without questioning the...
Chapter
Full-text available
In this book chapter, we observe an exceptional example of addressing messy and ill-defined problems through several disciplinary lenses during the ColLaboratoire 2016 Summer School (https://collaboratoire.cognovo.eu). We discuss the requirements and conditions under which this approach is an effective and appropriate alternative to mono-disciplina...
Conference Paper
Emotional expressivity can boost trust in human-human and human-machine interaction. As a multimodal phenomenon, previous research argued that a mismatch in the expressive channels provides evidence of joint audio-video emotional processing. However, while previous work studied this from the point of view of emotion recognition and processing, not...
Conference Paper
Full-text available
The use of speech as an interaction modality has grown considerably through the integration of Intelligent Personal Assistants (IPAs- e.g. Siri, Google Assistant) into smartphones and voice based devices (e.g. Amazon Echo). However, there remain significant gaps in using theoretical frameworks to understand user behaviours and choices and how they...
Data
Auxiliary materials for the paper ‘Can you tell the robot by the voice? An exploratory study on the role of voice in the perception of robots’ presented at HRI 2019. The file contains the full statistics tables of the data reported in the article.
Conference Paper
Correctly interpreting an interlocutor's emotional expression is paramount to a successful interaction. But what happens when one of the interlocutors is a machine? The facilitation of human-machine communication and cooperation is of growing importance as smartphones, autonomous cars, or social robots increasingly pervade human social spaces. Prev...
Chapter
Full-text available
Enhancing human-machine interaction by adding emotions to the machine‘s way of expression is one of the main topics of current research. This would improve the interaction, on the assumption that the more human-like the machine behavior is, the more comfortable the interaction with it will be. This project aims to create an environment-aware emotio...
Article
Full-text available
The 11th Summer Workshop on Multimodal Interfaces eNTERFACE 2015 was hosted by the Numediart Institute of Creative Technologies of the University of Mons from August 10th to September 2015. During the four weeks, students and researchers from all over the world came together in the Numediart Institute of the University of Mons to work on eight sele...
Article
Full-text available
With advances in research environments and the accompanying increase in the complexity of research projects, the range of skills required to carry out research calls for an increase in interdisciplinary and collaborative work. CogNovo, a doctoral training program for 25 PhD students, provided a unique opportunity to observe and analyze collaborativ...
Conference Paper
Full-text available
In this paper we present the AmuS database of about three hours worth of data related to amused speech recorded from two males and one female subjects and contains data in two languages French and English. We review previous work on smiled speech and speech-laughs. We describe acoustic analysis on part of our database, and a perception test compari...
Conference Paper
Full-text available
Prosodic information is known to play a role in personality attributions, such as judgements of trustworthiness. Research so far has focused on assessing the determinants of such attributions in static contexts, very often in the form of questionnaires, and not much is known about their dynamics, in particular, how direct experience of behaviour ov...
Article
Full-text available
The ability to communicate complex meanings is a specific human ability which plays a crucial role in social interactions. A habitual example of these interactions is conversation. However, we observe that spontaneous conversation often hits an impasse when none of the interlocutors immediately produces a follow-up utterance. The existence of impas...
Conference Paper
Full-text available
Speakers' accents have been claimed to influence initial judgements of personality traits, such as trustworthiness. We examined how personal experience with specific accents may serve to modify initial trust attributions, using an iterated trust game in which participants make investments with virtual players. The virtual player's accent was either...
Conference Paper
Full-text available
This study investigates phonetic aspects in the production and perception of Smiling Voice, i.e. speech accompanied by smiling. A new corpus of spontaneous conversations is recorded to compare the formant frequencies of Smiling Voice (SV) and Non-Smiling Voice (NSV); the hypothesis that smiling raises formant frequencies is proven to be valid also...

Questions

Question (1)
Question
I recently ran an experiment (let's call it experiment A) where I got 500+ participants. Afterwards, I changed the experimental manipulations 2 more times (resulting in experiments B and C). Experiment B has 120 participants, and experiment C has 80. (The experiments were ran in a museum so I had no control over how many participants I would get in a day). Now I would like to compare the results of experiment A (which have already been published) to those of experiments B and C. My analysis consists of an ordinal mixed-effects regression. How can I compare them, given that the sample sizes are so different? Would it be better to randomly sample 80 participants from experiments A and B, and compare them with C, or rather bootstrap experiments B and C until I get 500 participants? Or should I just ran separate analyses on the 3 experiments with the full participant samples, and then compare the effect sizes? Thanks!

Network

Cited By

Projects

Projects (2)
Project
Many robots are being built and deployed with the intention of communicating verbally with people, since this would provide a natural, hands-free communication method for many users. However, while a lot of research has been dedicated to implementing natural language capabilities in robots, for example in terms of what to say, and when, not much has been done on how robots should say it. But voice conveys a lot of information by itself too, for example information about the speaker -- e.g. where they are from, their affective state etc. -- but also paralinguistic information -- e.g. communicating urgency or stressing a certain word. So designing appropriate robot voices is important, as it can affect how a certain message from the robot is perceived.
Project
The challenges facing society today demand innovative approaches, creative solutions and wider resonances that can only be obtained by drawing on multiple perspectives. Cognitive innovation is an interdisciplinary approach that aims to disrupt single-field research in cognition, creativity, and innovation.