html5 templates




Conference Progamme

The following is a preliminary programme. Paper slots are subject to change depending on author availability.

All talks will take place in the Paccar Theatre in Science Gallery Dublin

* Denotes the listed presenters.

Day 1 - Thursday 22nd August

08:15 - 09:00                             Registration


09:00 - 09:10                             Welcome to CUI 2019

                                                       Benjamin Cowan & Leigh Clark (CUI 2019 General Chairs)


09:10 -  10:15                              Keynote 1: Cosmin Munteanu (University of Toronto Mississauga)

                                                       My dearest Alexa, would you be so kind as to let me know what the bloody weather                                                              may be  today?

                                                      Oscar Wilde once said: “Conversation about the weather is the last refuge of the                                                                             unimaginative.” This suggests that, for more than four decades, the design and                                                                               development of interfaces that allow humans to interact more naturally with machines had                                                         a significant creativity deficit. While in the early days of dialogue systems and interactive                                                             voice responsive applications this could have been largely attributed to engineering                                                                       limitations, our current expectations and needs challenge our views of what                                                                                     (speech-based) conversational interfaces can and should do for us – beside informing us                                                             about the weather. In this talk, I argue that, while currently available interfaces do indeed                                                             demonstrate technological progress, inertia in both design and engineering efforts has                                                                 lead to interfaces that have yet to reach the holy grail: seamless interactions with new                                                                 media, information, and devices, through natural modalities that transcend the confines of                                                         conventional interfaces. The consequences of this are particularly evident within contexts                                                         where natural, conversational interfaces may help marginalized users that stand to benefit                                                         the most from such technologies, yet fail to sustainably do so. Grounded in more than two                                                           decades of research in this space, I deconstruct in this talk some of the claims and myths                                                           about spoken conversational interfaces that hold us back from designing truly useful                                                                   applications. I then discuss how we may approach the design of such interfaces in ways                                                               that are not only more imaginative, but that will also lead to the emergence of interactions                                                         that are more meaningful and more inclusive to a broader range of users and contexts.


10:15 -  11:10                               Coffee Break


11:10 - 12:00                               Paper Session 1: Chatbots

                                                       Chair: Joel Fischer

11:10 - 11:30                                Typefaces and the Perception of Humanness in Natural Language Chatbots

                                                       Heloisa Candello*, Claudio Pinhanez, Flavio Figueiredo

11:30 - 11:40                                Chatbots as Unwitting Actors

                                                       Allison Perrone, Justin Edwards*

11:40 - 12:00                               Can Direct Address Affect User Engagement with Chatbots Embodied in Physical Spaces?

                                                       Heloisa Candello*, Claudio Pinhanez, Mauro Pichiliani, Marisa Vasconcelos, Haylla Conde


12:00 - 13:00                               Lunch


13:00 - 14:30                             Paper Session 2: IPA Use

                                                       Chair: Mary Ellen Foster

13:00 - 13:20                               Patient and Consumer Safety Risks When Using Conversational Assistants for Medical                                                               Information: An Observational Study of Siri, Alexa, and Google Assistant

                                                       Timothy Bickmore*, Ha Trinh, Stefan Olafsson, Teresa O'Leary, Reza Asadi,                                
                                                       Nathaniel Rickles, Ricardo Cruz

13:20 - 13:40                               Voice Interfaces in Everyday Life

                                                       Martin Porcheron*, Joel Fischer, Stuart Reeves, Sarah Sharples

13:40 - 14:00                               Multitasking with Alexa: How Using Intelligent Personal Assistants Impacts Language-                                                               based Primary Task Performance

                                                       Justin Edwards*, He Liu Liu, Tianyu Zhou, Sandy Gould, Leigh Clark, Phillip Doyle,     
                                                       Benjamin R. Cowan

14:00 - 14:10                               Finding Contextual Meaning of the Wake Word

                                                       Hyunhoon Jung*, Hyeji Kim                    

14:10 - 14:20                               Inquisitive Mind: A Conversational News Companion

                                                       Mateusz Dubiel*, Alessandra Cervone, Giuseppe Riccardi

14:20 - 14:30                               Voice Assistants and Older People: Some Open Issues

                                                        Sergio Sayago*, Barbara Barbosa, Benjamin R. Cowan


14:30 - 15:00                               Coffee Break


15:00 - 16:10                               Paper Session 3: Dialogue & Conversational Principles

                                                        Chair: Susan E. Brennan

15:00 - 15:20                                Explorations in multiparty casual social talk and its relevance for social human machine                                                         dialogue

                                                        Emer Gilmartin*, Benjamin R. Cowan, Carl Vogel, Nick Campbell

15:20 - 15:30                                I Don’t Know What You’re Talking About, HALexa

                                                        Christine Murad*, Cosmin Muntenau

15:30 - 15:40                                Conversational design considered harmful?

                                                        Stuart Reeves*

15:40 - 15:50                                How language works and what machines can do about it

                                                        Peter Wallis*, Bruce Edmonds

15:50 - 16:00                                Shoehorning in the Name of Science

                                                        Jens Edlund*


16:05 - 17:15                                 Industry Panel

                                                        Chair: Cosmin Munteanu

                                                        Panelists: Grace Hughes (Fjord @ The Dock), Andrew Ku (Google), Conor Whelan (Voysis)


17:15 - 18:15                                  Partner Expo & Drinks Reception


20:00 - late                                   Dinner at Drury Buildings

                                                         All guests to be seated by 20:00. 

Day 2 - Friday 23rd August

09:00 - 10:30                             Paper Session 4: System Development & Multimodality

                                                        Chair: Sergio Sayago

09:00 - 09:20                              Trust in artificial voices: A “congruency effect” of first impressions and behavioural                                                        experience

                                                        Ilaria Torre*

09:20 - 09:40                              Patters of Gaze in Speech Agent Interaction

                                                        Razan Jaber*, Donald McMillan, Jordi Solsona Belenguer, Barry Brown

09:40 - 10:00                               Crowdsourcing a self-evolving dialog graph

                                                        Patrik Jonell*, Per Fallgren, Fethiye Irmak Doğan, José Lopes, Ulme Wennberg, 
                                                        Gabriel Skantze

10:00 - 10:10                                Conversation is Multimodal - Thus Conversational User Interfaces should be as well

                                                        Stefan Schaffer*, Norbert Reithinger

10:10 - 10:20                                Face-to-Face Conversation: Why Embodiment Matters for Conversational User Interfaces

                                                        Mary Ellen Foster*


10:30 - 11:00                                Coffee Break


11:00 - 12:10                                 Paper Session 5: Ethics, Privacy & Trust

                                                        Chair: Timothy Bickmore

11:00 - 11:20                                “It’s Small Talk, Jim, But Not as We Know It.” Engendering Trust through Human-Agent                                                         Conversation in an Autonomous, Self-Driving Car

                                                        David R Large, Leigh Clark*, Gary Burnett, Kyle Harrington, Jacob Luton, Peter Thomas,                                                         Pete Bennett

11:20 - 11:30                                 A Need for Trust in Conversational Interface Research

                                                        Justin Edwards*, Elaheh Sanoubari

11:30 - 11:40                                 “I am from all over the world”: Moving towards a healthier voice enabled internet by                                                        acknowledging how it is built

                                                        Selina Jeanne Sutton*

11:40 - 11:50                                 From sex and therapy bots to virtual assistants and tutors: How emotional should                                                        artificially intelligent agents be?

                                                        Stella George*

11:50 - 12:00                                Issues Relating to Trust in Care Agents for the Elderly

                                                        Brendan Spillane*, Emer Gilmartin, Christian Saam, Vincent Wade

12:00 - 12:10                                Who owns your voice? Ethically sourced voices for non-commercial TTS applications

                                                        Kristen Scott*, Simone Ashby, David Braude, Matthew Aylett


12:10 - 13:10                                 Lunch


13:10 - 14:40                              Paper Session 6: Voice & Language Design

                                                         Chair: Christine Murad

13:10 - 13:30                                 Siri, Echo and Performance: You have to Suffer Darling

                                                        Matthew Aylett*, Benjamin R. Cowan, Leigh Clark

13:30 - 13:50                                Progressivity for Voice Interface Design

                                                        Joel Fischer*, Stuart Reeves, Martin Porcheron, Rein Sikveland

13:50 - 14:10                                 What’s in an accent? The impact of accented synthetic speech on lexical choice in                                                          human-machine dialogue

                                                         Benjamin R. Cowan*, Philip Doyle, Justin Edwards, Diego Garaialde, Ali Hayes-Brady,            
                                                         Holly P. Branigan, João Cabral, Leigh Clark

14:10 - 14:30                                 Entertaining and Opinionated but Too Controlling: A Large-Scale User Study of an Open                                                         Domain Alexa Prize System

                                                         Kevin Bowden*, Jiaqi Wu, Wen Cui, Juraj Juraska, Vrindavan Harrison, Brian Schwarzmann,                                                          Nicholas Santer, Stephen Whittaker, Marilyn Walker

14:30 - 14:40                                The Right Kind of Unnatural: Designing a Robot Voice

                                                         Matthew Aylett*, Selina Jeanne Sutton, Yolanda Vazquez Alvarez


14:40 - 15:10                                 Coffee Break


15:10 - 16:15                                 Keynote 2: Susan E. Brennan (The State University of New York at Stony Brook)

                                                         Can Machines Learn to Converse? What We Know from >30 Years of                                                          "Conversational Interfaces" 

                                                         Deep learning has revolutionized automated speech recognition. But what about spoken                                                          conversation - can machines learn to converse with people?  Because models are only as                                                          good as the data they're trained on, the answer to that question depends on (at least) two                                                          things: what your theory of conversation is, and how well-represented conversational                                                          processes are by the artifacts and evidence present in the input data.  I will consider                                                          conversational processes such as interpersonal coordination, repairs, multimodal cues,                                                          the joint construction of meaning, entrainment, and audience design.  Just as learning in                                                          the domain of image recognition is tainted by unintended biases, learning for spoken                                                          dialogue is tainted by a lack of indexical content in the input data. Fortunately, people are                                                          adaptable and can cope with many kinds of interactive partners, as long as there is                                                          transparency in how the partners present themselves.


16:15 - 16:55                                  Close & Handover to CUI 2020