Login / Signup

MAIN-VC: Lightweight Speech Representation Disentanglement for One-shot Voice Conversion.

Pengcheng LiJianzong WangXulong ZhangYong ZhangJing XiaoNing Cheng
Published in: CoRR (2024)
Keyphrases
  • lightweight
  • text to speech
  • communication infrastructure
  • emotion recognition
  • development environments
  • speech recognition
  • voice activity detection
  • vc dimension
  • speech synthesis
  • prosodic features