Login / Signup

Nonparallel Expressive TTS for Unseen Target Speaker using Style-Controlled Adaptive Layer and Optimized Pitch Embedding.

Mohammed Salah Al-RadhiTamás Gábor CsapóGéza Németh
Published in: SpeD (2023)
Keyphrases
  • text to speech
  • prosodic features
  • neural network
  • training set
  • speech recognition
  • multi layer
  • vector space
  • previously unseen
  • error correction
  • data hiding
  • graph embedding
  • speaker verification