Research map / Video / Video generation
Hierarchical Codec Diffusion for Video-to-Speech Generation
Jiaxin Ye, Gaoxiang Cong, Chenhui Wang, Xin-Cheng Wen, Zhaoyang Li, Boyuan Cao, Hongming Shan
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 hierarchical low/high-level modeling with level-specific visual conditioning (ablation) | HiCoDiT · LRS3 | WER: 30.65 -> 29.41 | Improved |
| add hierarchical modeling (ablation) | HiCoDiT · LRS2 | WER: 44.57 -> 39.99 | Improved |
| add dual-scale AdaLN instead of vanilla pooled AdaLN (ablation) | HiCoDiT · LRS3 | EmoAcc: 78.55 -> 79.41 | Improved |
| add dual-scale AdaLN instead of vanilla pooled AdaLN (ablation) | HiCoDiT · LRS2 | EmoAcc: 68.61 -> 68.21 | Mixed |
| add GE2E identity alignment loss (ablation) | HiCoDiT · LRS3 | speaker similarity: 34.10 -> 56.78 | Improved |
| add GE2E identity alignment loss (ablation) | HiCoDiT · LRS3 | WER: 29.38 -> 29.41 | No clear effect |
| use Poster2 instead of Poster for emotion features (ablation) | HiCoDiT · LRS3 | emotion accuracy: 76.29 -> 79.41 | Improved |
| provide speech as identity guidance (audio+video) vs video only | HiCoDiT · LRS3 | SpkSim: 0.5678 -> 0.6715 | Improved |
| HiCoDiT video-only vs FTV on speaker similarity | HiCoDiT · LRS3 | SpkSim: 0.5981 -> 0.5678 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- EmoDubber — EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing (CVPR 2025) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech (CVPR 2025 · similarity 0.90)
- Native Audio-Visual Alignment for Generation (NeurIPS 2026 · similarity 0.87)
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · similarity 0.87)
- OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking (NeurIPS 2025 · similarity 0.87)
- Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows (CVPR 2025 · similarity 0.86)
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (AAAI 2024 · similarity 0.86)
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.
