AI RESEARCH

VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories

arXiv CS.AI

ArXi:2604.10542v1 Announce Type: cross Video-to-Audio (V2A) generation is essential for immersive multimedia experiences, yet its evaluation remains underexplored. Existing benchmarks typically assess diverse audio types under a unified protocol, overlooking the fine-grained requirements of distinct audio categories.