NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Gabriel Mongaras Gabriel Mongaras
8.89K subscribers
834 views
39

 Published On May 27, 2024

Paper: https://arxiv.org/abs/2403.03100
Demo: https://speechresearch.github.io/natu...
Code: https://huggingface.co/spaces/amphion...

My notes: https://drive.google.com/file/d/1xnzE...

00:00 Intro
05:34 Architecture overview
18:45 GRL and subspace independence
24:45 Discrete diffusion Model
41:00 factorized diffusion model
44:00 Conclusion and results

show more

Share/Embed