Login / Signup

Applying Syntax-Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis.

Kei FurukawaTakeshi KishiyamaSatoshi Nakamura
Published in: CoRR (2022)
Keyphrases
  • speech synthesis
  • text to speech
  • speech recognition
  • prosodic features
  • neural network
  • vocal tract
  • data mining
  • learning algorithm
  • objective function
  • network architecture
  • constraint networks