This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.
WaveNet: A Generative Model for Raw Audio | DeepMind 
Added 2 years ago by Nitzan Hermon
Show info
WaveNet: A Generative Model for Raw Audio | DeepMind 
Info
This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.
2 Connections