Login / Signup

SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody.

Hui LuXixin WuZhiyong WuHelen Meng
Published in: ACM Multimedia (2023)
Keyphrases
  • end to end
  • user experience
  • content delivery
  • speech recognition
  • admission control
  • multimedia
  • reinforcement learning
  • video sequences
  • ad hoc networks
  • scalable video
  • text to speech