English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper reports on the GENEA Challenge 2023, in which participating teamsbuilt speech-driven gesture-generation systems using the same speech and motiondataset, followed by a joint evaluation. This year's challenge provided data onboth sides of a dyadic interaction, allowing teams to generate full-body motionfor an agent given its speech (text and audio) and the speech and motion of theinterlocutor. We evaluated 12 submissions and 2 baselines together withheld-out motion-capture data in several large-scale user studies. The studiesfocused on three aspects: 1) the human-likeness of the motion, 2) theappropriateness of the motion for the agent's own speech whilst controlling forthe human-likeness of the motion, and 3) the appropriateness of the motion forthe behaviour of the interlocutor in the interaction, using a setup thatcontrols for both the human-likeness of the motion and the agent's own speech.We found a large span in human-likeness between challenge submissions, with afew systems rated close to human mocap. Appropriateness seems far from beingsolved, with most submissions performing in a narrow range slightly abovechance, far behind natural motion. The effect of the interlocutor is even moresubtle, with submitted systems at best performing barely above chance.Interestingly, a dyadic system being highly appropriate for agent speech doesnot necessarily imply high appropriateness for the interlocutor. Additionalmaterial is available via the project website athttps://svito-zar.github.io/GENEAchallenge2023/ .

The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings