Virtual Conversational Characters:
Applications, Methods, and Research Challenges

http://www.vhml.org/workshops/HF2002/
29th November, 2002
Melbourne, Australia

in conjunction with
HF2002 and OZCHI2002
http://www.iceaustralia.com/HF2002/


The field of Virtual Conversational Characters (VCCs) is an emerging discipline that is growing in importance, both in industry and the research community. A VCC could be an avatar representing a user in virtual meeting spaces such as chat rooms or MUDs, a part of the Human Computer Interface between user and application/web-page or, in some cases, the ultimate interface metaphor to information and computer-based services.

A VCC is an embodied conversational agent whose audio-visual appearance and behaviour may vary dependant upon the:

This is a multidisciplinary field that embraces HCI, graphics and animation, embodied agents, dialogue management, machine learning, markup languages to direct the VCC, text-to-speech synthesis (and perhaps speech-to-text for input), etc. Companies as well as researchers are developing VCC systems and applying the VCCs as sophisticated intelligent interfaces to applications and Web pages as well as creating Virtual Lecturers in education, Virtual Salespersons in e-commerce, Virtual Actors and 3rd Person avatars in entertainment and computer games, Web Interface Agents, News Presenters, etc.

It is crucial that this development is paralleled by evaluation. Too many of these interfaces or "helping assistants" have been ineffectual or invoked hostility in users because of developer's lack of understanding about basic acceptance criteria such as effectiveness, usability, trust, etc.

This workshop will bring both established and new researchers together to discuss the development, implementation and evaluation of VCC interface systems, the current VCC state-of-the-art and to create a vision for the future of VCC interface technology.

The origin of this workshop dates from a successful workshop on Talking Head Technology organised for the OZCHI 2001 conference. This was followed by a second held in Bruxelles in 2001 on the Virtual Human Markup Language - an XML based language for directing Virtual Humans and giving them emotions/gestures. A third workshop is to follow in Bologna in mid 2002 on Embodied conversational agents - let's specify and evaluate them! for AAMAS 2002.

MAJOR TOPICS include (but are not limited to)

WORKSHOP FORMAT

The full day workshop will feature a mix of paper presentations, demonstrations, and discussion rounds. The presentations should cover one of the several themes of the workshop and should be oriented toward:

The workshop will conclude with a panel discussion of:

WORKSHOP DEMONSTRATIONS & EXHIBITS

We strongly encourage you to demonstrate your work and to provide URLs to permanent web sites that contain examples of your system.

To give us time to organize the technical requirements, if you are to demonstrate your system, we must be notified before YYY. Contact us for details at: raytrace@vhml.org

WORKSHOP OUTCOMES

At the end of the workshop, participants should have a broad understanding of the differing technologies involved in the production, development and directing of VCC interface systems and applications. They will have seen several VCC systems and will understand the problems associated with the technology. They will have contributed, through discussion, to the future development of VCC interfaces within the global context. They will also become part of a network of VCC researchers and practitioners.