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%.
"Banks, governments, credit card companies and fintech evangelists all want us to believe a cashless future is inevitable and good. But this isn't a frictionless utopia says Brett Scott, and it's time to fight back."