Login / Signup

Wav2Seq: Pre-Training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages.

Felix WuKwangyoun KimShinji WatanabeKyu Jeong HanRyan McDonaldKilian Q. WeinbergerYoav Artzi
Published in: ICASSP (2023)
Keyphrases
  • low complexity
  • successive approximation
  • motion estimation
  • expressive power
  • decoding process
  • training set
  • probabilistic model
  • structured prediction
  • error control