WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

WaveGrad 2 is a non-autoregressive generative model for text-to-speech synthesis. It is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence.

Data and Resources

Cite this as

Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, Najim Dehak, William Chan (2024). Dataset: WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis. https://doi.org/10.57702/ugwouiz9

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Nanxin Chen
More Authors
Yu Zhang
Heiga Zen
Ron J. Weiss
Mohammad Norouzi
Najim Dehak
William Chan
Homepage https://wavegrad.github.io/v2