Parallel WaveNet: Fast High-Fidelity Speech Synthesis

Yazhe Li
Yazhe Li
Igor Babuschkin
Igor Babuschkin
George van den Driessche
George van den Driessche
Luis C. Cobo
Luis C. Cobo
Florian Stimberg
Florian Stimberg
Norman Casagrande
Norman Casagrande
Dominik Grewe
Dominik Grewe

international conference on machine learning, 2018.

Cited by: 355|Bibtex|Views317
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to todayu0027s massively p...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments