Login / Signup

MixGAN-TTS: Efficient and Stable Speech Synthesis Based on Diffusion Model.

Yan DengNing WuChengjun QiuYangyang LuoYan Chen
Published in: IEEE Access (2023)
Keyphrases
  • speech synthesis
  • text to speech
  • diffusion model
  • prosodic features
  • speech recognition
  • information diffusion
  • laplace transform
  • vocal tract