A latent diffusion model for speech enhancement that also learns to generate background noise, improving quality and generalization to unseen noise with fewer diffusion steps.
The proposed cLDM operates in a low- dimensional latent space, reducing complexity and improving the efficiency of the generation process
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning
A latent diffusion model for speech enhancement that also learns to generate background noise, improving quality and generalization to unseen noise with fewer diffusion steps.