Login / Signup

Make-A-Voice: Unified Voice Synthesis With Discrete Representation.

Rongjie HuangChunlei ZhangYongqi WangDongchao YangLuping LiuZhenhui YeZiyue JiangChao WengZhou ZhaoDong Yu
Published in: CoRR (2023)
Keyphrases
  • machine learning
  • continuous domains
  • text to speech
  • multi valued
  • data sets
  • databases
  • artificial intelligence
  • three dimensional
  • texture synthesis
  • emotion recognition
  • voice recognition
  • voice activity detection