Sign in

U-Style: Cascading U-nets with Multi-level Speaker and Style Modeling for Zero-Shot Voice Cloning.

Tao LiZhichao WangXinfa ZhuJian CongQiao TianYuping WangLei Xie
Published in: CoRR (2023)
Keyphrases
  • social networks
  • real world
  • genetic algorithm
  • artificial intelligence
  • knowledge base
  • feature extraction
  • speaker recognition
  • real time
  • databases
  • computer vision
  • multi layer
  • modeling framework
  • authorship attribution