AI RESEARCH
Hierarchical Codec Diffusion for Video-to-Speech Generation
arXiv CS.CV
•
ArXi:2604.15923v1 Announce Type: cross Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals. However, existing VTS methods disregard the hierarchical nature of speech, which spans coarse speaker-aware semantics to fine-grained prosodic details. This oversight hinders direct alignment between visual and speech features at specific hierarchical levels during property matching.