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

Current talking avatars mostly generate co-speech gestures based on audio andtext of the utterance, without considering the non-speaking motion of thespeaker. Furthermore, previous works on co-speech gesture generation havedesigned network structures based on individual gesture datasets, which resultsin limited data volume, compromised generalizability, and restricted speakermovements. To tackle these issues, we introduce FreeTalker, which, to the bestof our knowledge, is the first framework for the generation of both spontaneous(e.g., co-speech gesture) and non-spontaneous (e.g., moving around the podium)speaker motions. Specifically, we train a diffusion-based model for speakermotion generation that employs unified representations of both speech-drivengestures and text-driven motions, utilizing heterogeneous data sourced fromvarious motion datasets. During inference, we utilize classifier-free guidanceto highly control the style in the clips. Additionally, to create smoothtransitions between clips, we utilize DoubleTake, a method that leverages agenerative prior and ensures seamless motion blending. Extensive experimentsshow that our method generates natural and controllable speaker movements. Ourcode, model, and demo are are available at\url{https://youngseng.github.io/FreeTalker/}.

Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness