Login / Signup

MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis.

Wenhao GuanYishuang LiTao LiHukai HuangFeng WangJiayan LinLingyan HuangLin LiQingyang Hong
Published in: CoRR (2023)
Keyphrases
  • multi modal
  • text to speech
  • text to speech synthesis
  • multi modality
  • word processing
  • high dimensional
  • audio visual
  • cross modal
  • feature selection
  • image annotation
  • humanoid robot
  • semantic concepts
  • fusing multiple