Explicitly modeling the posterior transition in diffusion-based speech enhancement, including a noisy-speech diffusion that makes the likelihood tractable, improves unsupervised enhancement and robustness to domain shift.
Speech enhancement and dereverberation with diffusion-b ased genera- tive models,
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
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
Explicitly modeling the posterior transition in diffusion-based speech enhancement, including a noisy-speech diffusion that makes the likelihood tractable, improves unsupervised enhancement and robustness to domain shift.