The availability of data in expressive styles across languages is limite...
State-of-the-art text-to-speech (TTS) systems require several hours of
r...
We address the problem of cross-speaker style transfer for text-to-speec...
Artificial speech synthesis has made a great leap in terms of naturalnes...
This paper proposes a general enhancement to the Normalizing Flows (NF) ...
We present a universal neural vocoder based on Parallel WaveNet, with an...
Recently the state-of-the-art text-to-speech synthesis systems have shif...