AI Paper Atlas

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

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 1 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 hierarchical low/high-level modeling with level-specific visual conditioning (ablation)HiCoDiT · LRS3WER: 30.65 -> 29.41Improved
add hierarchical modeling (ablation)HiCoDiT · LRS2WER: 44.57 -> 39.99Improved
add dual-scale AdaLN instead of vanilla pooled AdaLN (ablation)HiCoDiT · LRS3EmoAcc: 78.55 -> 79.41Improved
add dual-scale AdaLN instead of vanilla pooled AdaLN (ablation)HiCoDiT · LRS2EmoAcc: 68.61 -> 68.21Mixed
add GE2E identity alignment loss (ablation)HiCoDiT · LRS3speaker similarity: 34.10 -> 56.78Improved
add GE2E identity alignment loss (ablation)HiCoDiT · LRS3WER: 29.38 -> 29.41No clear effect
use Poster2 instead of Poster for emotion features (ablation)HiCoDiT · LRS3emotion accuracy: 76.29 -> 79.41Improved
provide speech as identity guidance (audio+video) vs video onlyHiCoDiT · LRS3SpkSim: 0.5678 -> 0.6715Improved
HiCoDiT video-only vs FTV on speaker similarityHiCoDiT · LRS3SpkSim: 0.5981 -> 0.5678Hurt

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.

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

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