Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture

Documenti analoghi

• Investigating Training Objectives for Generative Speech Enhancement
  di: Richter, Julius, et al.
  Pubblicazione: (2024)
• LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models
  di: Richter, Julius, et al.
  Pubblicazione: (2025)
• The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement
  di: de Oliveira, Danilo, et al.
  Pubblicazione: (2024)
• Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
  di: de Oliveira, Danilo, et al.
  Pubblicazione: (2024)
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
  di: Lemercier, Jean-Marie, et al.
  Pubblicazione: (2022)