Tacotron 2
Tacotron 2
a neural network architecture for speech synthesis directly from text.
Multispeaker Text-To-Speech Synthesis
a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training
Flowtron (Flow based model)
Auto-regressive flow-based generative network for text to speech synthesis
https://www.youtube.com/watch?v=bOf2S7OzFEg