Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Vadim Popov * 1 Ivan Vovk * 1 2 Vladimir Gogoryan 1 2 Tasnima Sadekova 1 Mikhail Kudinov 1
Abstract 2014) and Normalizing Flows (Rezende & Mohamed, 2015)
Recently, denoising diffusion probabilistic mod- were used in the design of TTS engines for a parallel gener-
els and generative score matching have shown ation with comparable quality of the synthesized speech.
high potential ...


雷达卡




京公网安备 11010802022788号







