AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

Yihao Zhi, Xiaodong Cun, Xuelin Chen, Xi Shen, Wen Guo, Shaoli Huang, Shenghua Gao

ICCV 2023 · Image generation › Autoregressive and latent generation · approach: Neural text-to-speech synthesis · 46 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 diffusion rhythm-aware refinement to semantic-aware generator (ablation)SAG · TED GestureFGD: 56.878 -> 8.446Improved
use FFT-synthesized data beat alignment network instead of diffusion RAG (ablation)SAG · TED GestureFGD: 56.878 -> 65.718Hurt
replace MLP denoiser with transformer decoder (ablation)RAG · TED GestureBC: 0.656 -> 0.418Hurt
use 1D conv waveform audio encoder instead of Mel-spectrogram 2D conv (ablation)RAG · TED GestureFGD: 4.951 -> 2.152Improved
add KL divergence loss on style embedding (ablation)RAG · TED GestureFGD: 5.256 -> 2.152Improved
use SiLU activation instead of ReLU or LeakyReLU (ablation)RAG MLP blocks · TED GestureFGD: 3.956 -> 2.152Improved
use 4 MLP layers instead of 2, 6 or 8 (ablation)RAG · TED GestureFGD: 3.047 -> 2.152Improved
increase classifier-free guidance weight w (ablation)Ours Rhythm · TED GestureBC and Diversity: BC 0.656 -> 0.699; FGD 2.152 -> 6.622Mixed
add beat empowerment to SAG gestures in the full system vs rhythm-onlyOurs Full vs Ours Rhythm · TED GestureFGD: 2.152 -> 11.310Hurt
two-stage semantic plus rhythm generator vs end-to-end baselinesLivelySpeaker · TED Gesture user studynaturalness preference: 42.7% for Ours Full vs 41.6% for S2GImproved

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