Login / Signup

Unit selection speech synthesis using multiple speech units at non-adjacent segments for prosody and waveform generation.

Masatsune TamuraNorbert BraunschweilerTakehiko KagoshimaMasami Akamine
Published in: ICASSP (2010)
Keyphrases
  • speech synthesis
  • speech recognition
  • text to speech
  • vocal tract
  • prosodic features
  • speech corpus
  • neural network
  • language model
  • processing units
  • real time
  • cross correlation
  • automatic speech recognition