List your company

Image-to-Audio on VGGSound (test)

2.61KL DivergenceIm2Wav
2.60042.66522.732.7948Jun 10, 2026

Evaluation results

MethodLinks
Im2Wav2026.062.617.0619.637.5841
Seeing&Hearing2026.062.696.1520.966.8729
Caption2Audio2026.062.767.4832.975.5421
AudioX-Basetraining_mode=no specific training with image data2026.062.8111.4717.032.6822
AudioX-Turbotraining_mode=no specific training with image data2026.062.8511.2216.532.6523