SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping

Proposed SpecGrad that adapts the spectral envelope of diffusion noise based on the conditioning log-mel spectrogram.

Data and Resources

Cite this as

Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani (2024). Dataset: SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping. https://doi.org/10.57702/ahbe0977

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2203.16749
Author Yuma Koizumi
More Authors
Heiga Zen
Kohei Yatabe
Nanxin Chen
Michiel Bacchiani
Homepage https://wavegrad.github.io/specgrad/