SSV2A: Source Specific Vision to Audio Generation

We demonstrate more generated samples of SSV2A in this page. Please visit the project page for an overview.

Image-to-Audio Generation

Judge + Bird

Pistol + Fish

Fireman + Car

Lion + Doctor

Diver + Fire

Pigeon + Frog

Fireside Guitar

Street Talking

Baby etc.

Video-to-Audio Generation

Pigeons

Stadium

Cows

Accident

Fingerboard