Entrainment is the phenomenon by which an interlocutor adapts their spea...
We present an SVQ-VAE architecture using a split vector quantizer for NT...
Recently the state-of-the-art text-to-speech synthesis systems have shif...
Recent advances in Text-to-Speech (TTS) have improved quality and natura...
We present a neural text-to-speech system for fine-grained prosody trans...