Sign in

An F0 modeling technique based on prosodic events for spontaneous speech synthesis.

Tomoki KoriyamaTakashi NoseTakao Kobayashi
Published in: ICASSP (2012)
Keyphrases
  • speech synthesis
  • speech recognition
  • prosodic features
  • text to speech
  • vocal tract
  • real time
  • data sets
  • modeling framework
  • database
  • hidden markov models