Login / Signup

Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder.

Eunwoo SongMin-Jae HwangRyuichi YamamotoJin-Seob KimOhsung KwonJae-Min Kim
Published in: INTERSPEECH (2020)
Keyphrases
  • text to speech
  • speech synthesis
  • neural network
  • network architecture
  • modeling method
  • modeling language
  • data sets
  • general purpose
  • prosodic features