Composite audio comparisons with state-of-the-art methods

Example 7 Back to index

Captions for each audio tracks (all sounds should be contained)

  1. The seal slides smoothly into the water
  2. The child claps enthusiastically
  3. The trainer speaks clearly to the audience
  4. The water splashes softly as the seal moves
  5. The crowd murmurs excitedly
MMAudio + NAG (ours) MMAudio MMAudio + Negative prompting
Seeing-and-Hearing FoleyCrafter FoleyCrafter + Negative prompting