Open access
Jul 2026
AudioVAE-MASR: A Continuous-Latent Masked Autoregressive Framework for Multi-Distortion Speech Restoration
The study presents AudioVAE-MASR as a transparent continuous-latent restoration framework and identifies the fidelity-control problems that must be solved before such generative restoration can match the strongest lightweight discriminative systems.
Fuqiang Hu, Yi Guo, Hanbing Tian
· Applied Sciences · 0 citations