AI Paper Atlas

Research map / Video / Video generation

All You Need is Your Voice: Emotional Face Representation with Audio Perspective for Emotional Talking Face Generation

Seongho Kim, Byung Cheol Song

ECCV 2024 · Video › Video generation · approach: Talking face generation · 3 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add frame-wise emotional intensity regression loss (Linten) (ablation)EAP · MEADintensity RMSE: 0.69 -> 0.35Improved
add intensity regression loss (ablation)EAP · MEADLMD: 4.68 -> 3.60 (-0.94 stated)Improved
add N-pair metric loss for neutralization (Lmetric) (ablation)EAP · MEADintensity RMSE: 0.69 -> 0.49Improved
combine metric loss and intensity regression loss (ablation)EAP · MEADCCC: 0.32 -> 0.61Improved
combine metric loss and intensity regression loss (ablation)EAP · MEADFID: 20.64 -> 15.34Improved
add ERA (emotion representation from audio) on top of ANT (ablation)EAP-ANT · MEADFID: 28.01 -> 15.34Improved
EAP versus EAT on FIDEAP · LRWFID: 4.15 vs AVCT 2.99Hurt
EAP versus EAT for emotional intensity flowEAP · MEADRMSE / CCC: 0.28 lower RMSE, up to 0.47 higher CCCImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy