WaveNet and WaveRNN creates more natural-sounding speech for products used by millions of people around the world.
Du mal a déterminer si c'est nouveau, nouveau ou juste nouveau
WaveNet is a generative model that is trained on speech samples. It creates the waveforms of speech patterns by predicting which sounds likely follow each other. Each waveform is built one sample at a time, with up to 24,000 samples per second of sound.
via Deep Learning Weekly : lire l’article source