The emphasis on one-to-one speak/wait spoken conversational interaction with intelligent agents leads to long pauses between conversational turns, undermines the flow and naturalness of the interaction, and undermines the user experience. Despite ground breaking advances in the area of generating and understanding natural language with techniques such as LLMs, conversational interaction has remained relatively overlooked. In this workshop we will discuss and review the challenges, recent work and potential impact of improving conversational interaction with artificial systems. We hope to share experiences of poor human/system interaction, best practices with third party tools, and generate design guidance for the community.

The workshop will be of interest primarily for HAI attendees who work with spoken conversation as the main means of interaction between their systems and users. However, we also hope that attendees working with other modalities, who are curious about how spoken conversational interaction may improve or support their work, will also attend. We will ask all attendees to complete a mandatory one page expression of interest to help support workshop discussions.

Submission Information

Paper submission is optional. Eight accepted papers of sufficient quality, interest for the workshop, and ability to provoke discussion will be given a 10 minute presentation slot and will be optionally hosted on the workshop website. Submitted papers should be 3 to 4 pages long (including references), submitted in the CHI Extended Abstract format , and shouldn’t be published elsewhere before the workshop – but we are happy for it to be published elsewhere after the workshop.

For further information or to be added to the workshop email list please contact: Marta Romeo

Publication

Accepted papers will be posted to the workshop website ahead of the workshop date and serve as the basis for presentations and discussion at the workshop.