Login / Signup

Real-Time Neural Text-to-Speech with Sequence-to-Sequence Acoustic Model and WaveGlow or Single Gaussian WaveRNN Vocoders.

Takuma OkamotoTomoki TodaYoshinori ShigaHisashi Kawai
Published in: INTERSPEECH (2019)
Keyphrases
  • real time
  • text to speech
  • pattern recognition
  • maximum likelihood
  • general purpose
  • word processing