A team of researchers at NVIDIA has recently developed WaveGlow, a flow-based network that can generate high-quality speech from melspectrograms, which are acoustic time-frequency representations of sound. Their method, outlined in a paper pre-published on arXiv, uses a single network trained with a single cost function, making the training procedure easier and more stable.
from News on Artificial Intelligence and Machine Learning https://ift.tt/2Km0Nbz
Home
machine-learning-ai-news
News on Artificial Intelligence and Machine Learning
WaveGlow: A flow-based generative network to synthesize speech
- Blogger Comment
- Facebook Comment
Subscribe to:
Post Comments
(
Atom
)
0 comments:
Post a Comment