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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add visual context attention module (ablation) | VCA-GAN baseline · GRID multi-speaker | WER: 5.43% -> 5.02% | Improved |
| add visual context attention module (ablation) | VCA-GAN baseline · GRID multi-speaker | ESTOI: 0.584 -> 0.596 | Improved |
| add synchronization learning (ablation) | VCA-GAN baseline + VCA · GRID multi-speaker | WER: 5.02% -> 4.91% | Improved |
| add synchronization learning (ablation) | VCA-GAN baseline + VCA · GRID multi-speaker | ESTOI: 0.596 -> 0.601 | Improved |
| add multi-discriminators (ablation) | VCA-GAN baseline + VCA + sync · GRID multi-speaker | PESQ: 1.935 -> 1.961 | Improved |
| add multi-discriminators (ablation) | VCA-GAN baseline + VCA + sync · GRID multi-speaker | WER: 4.91% -> 4.80% | Improved |
| use VCA-GAN instead of Lip2Wav | GRID constrained-speaker · GRID | WER: 14.08% -> 12.25% | Improved |
| use VCA-GAN instead of Lip2Wav | GRID constrained-speaker · GRID | STOI: 0.731 -> 0.724 | No clear effect |
| use VCA-GAN instead of Lip2Wav (no speaker embedding) | LRW · LRW | PESQ: 1.197 -> 1.337 | Improved |
Closest papers by meaning
- SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory (AAAI 2022 · similarity 0.86)
- SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis (AAAI 2026 · similarity 0.86)
- Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video (ICCV 2023 · similarity 0.86)
- From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech (CVPR 2025 · similarity 0.84)
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.84)
- Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling (NeurIPS 2026 · similarity 0.84)
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.
