WaveNet
DeepMind's generative model of raw audio produces more natural speech than the best existing text-to-speech systems.
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%.
Official source
WaveNet: A generative model for raw audiodeepmind.google · published