Sign in

Articulatory-to-acoustic conversion using BLSTM-RNNs with augmented input representation.

Zheng-Chen LiuZhen-Hua LingLi-Rong Dai
Published in: Speech Commun. (2018)
Keyphrases
  • recurrent neural networks
  • representation scheme
  • speech recognition
  • visual speech recognition
  • knowledge base
  • expert systems
  • image representation