PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation
PRISM-Bench is presented, the first audio-centric diagnostic benchmark for T2AV generation and demonstrates that current generation paradigms overfit to perceptual fidelity while struggling with complex grounding and control tasks, particularly in generating music and synchronized On-screen audio.
Yu-Chen Sun, Qian Yang, Jun Wang et al.
· 0 citations