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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Speech-driven 3D facial animation has been an attractive task in bothacademia and industry. Traditional methods mostly focus on learning adeterministic mapping from speech to animation. Recent approaches start toconsider the non-deterministic fact of speech-driven 3D face animation andemploy the diffusion model for the task. However, personalizing facialanimation and accelerating animation generation are still two major limitationsof existing diffusion-based methods. To address the above limitations, wepropose DiffusionTalker, a diffusion-based method that utilizes contrastivelearning to personalize 3D facial animation and knowledge distillation toaccelerate 3D animation generation. Specifically, to enable personalization, weintroduce a learnable talking identity to aggregate knowledge in audiosequences. The proposed identity embeddings extract customized facial cuesacross different people in a contrastive learning manner. During inference,users can obtain personalized facial animation based on input audio, reflectinga specific talking style. With a trained diffusion model with hundreds ofsteps, we distill it into a lightweight model with 8 steps for acceleration.Extensive experiments are conducted to demonstrate that our method outperformsstate-of-the-art methods. The code will be released.

DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser