AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach

Chaitanya Ahuja, Dong Won Lee, Yukiko I. Nakano, Louis-Philippe Morency

ECCV 2020 · Image generation › Autoregressive and latent generation · approach: Neural text-to-speech synthesis · 116 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 mixture of sub-generators (M>1) (ablation)StAGE, 8 speakers · PATS style preservation (8 speakers, mean)Mode classification F1: 0.32 -> 0.33Improved
add mixture of sub-generators (M>1) (ablation)StAGE, 4 speakers · PATS style preservation (4 speakers, mean)Mode classification F1: 0.34 -> 0.35Improved
add mixture of sub-generators (M>1) (ablation)StAGE, 2 speakers · PATS style preservation (2 speakers, mean)PCK: 0.36 -> 0.34No clear effect
add mixture of sub-generators (ablation)StAGE, 8 speakers · PATS style transfer (8 speakers)Inception score: 3.89 -> 4.48Improved
add mixture of sub-generators (ablation)StAGE, 2 speakers · PATS style transfer (2 speakers)Inception score: 2.17 -> 2.61Improved
add mixture of sub-generators to single speaker model (M=1 to M=8) (ablation)CMix-GAN · PATS single speakerMode classification F1: 26.6 -> 28.0Improved
increase number of sub-generators from 8 to 12 (ablation)CMix-GAN · PATS single speakerMode classification F1: 28.0 -> 27.8No clear effect
add multiple speakers in training (single-speaker S2G to multi-speaker Mix-StAGE, 8 speakers)S2G · PATS style preservation (8 speakers, mean)PCK: 0.36 -> 0.40Improved
add style embedding and consistency loss with multi-speaker training (8 speakers) (ablation)CMix-GAN · PATS style preservation (8 speakers, mean)PCK: 0.37 -> 0.40Improved
use Mix-StAGE instead of MUNITMUNIT · PATS style transfer (8 speakers)Inception score: 2.06 -> 4.48Improved
increase number of training speakers from 2 to 8Mix-StAGE · PATS style transferInception score: 2.61 -> 4.48Improved
increase number of training speakers from 2 to 8 for style preservationMix-StAGE, individual speakers · PATS style preservationper-speaker PCK/F1Mixed

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