Waveglow: A flow-based generative network for speech synthesis
R Prenger, R Valle, B Catanzaro - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
R Prenger, R Valle, B Catanzaro
ICASSP 2019-2019 IEEE International Conference on Acoustics …, 2019•ieeexplore.ieee.orgIn this paper we propose WaveGlow: a flow-based network capable of generating high
quality speech from mel-spectrograms. WaveGlow combines insights from Glow [1] and
WaveNet [2] in order to provide fast, efficient and high-quality audio synthesis, without the
need for auto-regression. WaveGlow is implemented using only a single network, trained
using only a single cost function: maximizing the likelihood of the training data, which makes
the training procedure simple and stable. Our PyTorch implementation produces audio …
quality speech from mel-spectrograms. WaveGlow combines insights from Glow [1] and
WaveNet [2] in order to provide fast, efficient and high-quality audio synthesis, without the
need for auto-regression. WaveGlow is implemented using only a single network, trained
using only a single cost function: maximizing the likelihood of the training data, which makes
the training procedure simple and stable. Our PyTorch implementation produces audio …
In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow [1] and WaveNet [2] in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a single network, trained using only a single cost function: maximizing the likelihood of the training data, which makes the training procedure simple and stable. Our PyTorch implementation produces audio samples at a rate of more than 500 kHz on an NVIDIA V100 GPU. Mean Opinion Scores show that it delivers audio quality as good as the best publicly available WaveNet implementation. All code will be made publicly available online [3].
ieeexplore.ieee.org