Tweeted By @DeepMindAI

We've developed a new model for text-to-speech using GANs (TTS-GAN), combining high quality with efficient generation. More details in the paper: https://t.co/hJw2MVNEPZ, and the abstract as read by TTS-GAN: https://t.co/NjeNGtpU2i

— DeepMind (@DeepMindAI) September 26, 2019