pith. sign in

AlignDiT: Multimodal aligned dif- fusion transformer for synchronized speech generation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.SD 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Hierarchical Codec Diffusion for Video-to-Speech Generation

cs.SD · 2026-04-17 · unverdicted · novelty 7.0

HiCoDiT generates speech from video by conditioning low-level RVQ tokens on speaker identity and high-level tokens on facial expressions via a dual-scale normalized diffusion transformer.

citing papers explorer

Showing 1 of 1 citing paper.

  • Hierarchical Codec Diffusion for Video-to-Speech Generation cs.SD · 2026-04-17 · unverdicted · none · ref 6

    HiCoDiT generates speech from video by conditioning low-level RVQ tokens on speaker identity and high-level tokens on facial expressions via a dual-scale normalized diffusion transformer.