Stable Audio 3 develops fast latent diffusion models for variable-length audio generation and editing via a semantic-acoustic autoencoder and adversarial post-training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stable Audio 3
Stable Audio 3 develops fast latent diffusion models for variable-length audio generation and editing via a semantic-acoustic autoencoder and adversarial post-training.