Login / Signup

Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks.

Yun TangAnna Y. SunHirofumi InagumaXinyue ChenNing DongXutai MaPaden TomaselloJuan Pino
Published in: ACL (1) (2023)
Keyphrases
  • video codec
  • low complexity
  • error control
  • visual attention
  • distributed video coding
  • successive approximation
  • wyner ziv
  • noisy channel
  • rate distortion
  • image coding
  • motion compensated
  • hybrid models