AI RESEARCH
Real-Time Streamable Generative Speech Restoration with Flow Matching
arXiv CS.LG
•
ArXi:2512.19442v3 Announce Type: replace-cross Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still lagging behind due to their computation-heavy nature involving multiple calls of large DNNs.