Picture for Vladimir Gogoryan

Vladimir Gogoryan

Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

Add code
Sep 28, 2021
Figure 1 for Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Figure 2 for Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Figure 3 for Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Figure 4 for Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Viaarxiv icon

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

Add code
May 13, 2021
Figure 1 for Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Figure 2 for Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Figure 3 for Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Figure 4 for Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Viaarxiv icon