AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Lip to Speech Synthesis with Visual Context Attentional GAN

Minsu Kim, Joanna Hong, Yong Man Ro

NeurIPS 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 24 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 visual context attention module (ablation)VCA-GAN baseline · GRID multi-speakerWER: 5.43% -> 5.02%Improved
add visual context attention module (ablation)VCA-GAN baseline · GRID multi-speakerESTOI: 0.584 -> 0.596Improved
add synchronization learning (ablation)VCA-GAN baseline + VCA · GRID multi-speakerWER: 5.02% -> 4.91%Improved
add synchronization learning (ablation)VCA-GAN baseline + VCA · GRID multi-speakerESTOI: 0.596 -> 0.601Improved
add multi-discriminators (ablation)VCA-GAN baseline + VCA + sync · GRID multi-speakerPESQ: 1.935 -> 1.961Improved
add multi-discriminators (ablation)VCA-GAN baseline + VCA + sync · GRID multi-speakerWER: 4.91% -> 4.80%Improved
use VCA-GAN instead of Lip2WavGRID constrained-speaker · GRIDWER: 14.08% -> 12.25%Improved
use VCA-GAN instead of Lip2WavGRID constrained-speaker · GRIDSTOI: 0.731 -> 0.724No clear effect
use VCA-GAN instead of Lip2Wav (no speaker embedding)LRW · LRWPESQ: 1.197 -> 1.337Improved

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