Login / Signup

Emphatic Speech Generation with Conditioned Input Layer and Bidirectional LSTMS for Expressive Speech Synthesis.

Runnan LiZhiyong WuYuchen HuangJia JiaHelen MengLianhong Cai
Published in: ICASSP (2018)
Keyphrases
  • speech synthesis
  • speech recognition
  • text to speech
  • vocal tract
  • prosodic features
  • speech corpus
  • multi layer
  • input data
  • automatic speech recognition
  • user input
  • neural network
  • hidden markov models
  • application layer