no code implementations • 21 Jun 2021 • Minsu Kang, Sungjae Kim, Injung Kim
We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference.
no code implementations • 1 Apr 2021 • Minsu Kang, Jihyun Lee, Simin Kim, Injung Kim
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread.