AudioMorphix performs training-free local audio editing by morphing latents and applying energy guidance to a pretrained diffusion model, reporting state-of-the-art scores on its new AudioSet-E benchmark.
An edit friendly ddpm noise space: Inversion and manipula- tions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AudioMorphix: Training-free audio editing with diffusion probabilistic models
AudioMorphix performs training-free local audio editing by morphing latents and applying energy guidance to a pretrained diffusion model, reporting state-of-the-art scores on its new AudioSet-E benchmark.