Login / Signup
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition.
Rupak Vignesh Swaminathan
Brian King
Grant P. Strimel
Jasha Droppo
Athanasios Mouchtaris
Published in:
CoRR (2021)
Keyphrases
</>
speech recognition
learning process
speech understanding
pattern recognition
hidden markov models
natural language processing
language model
em algorithm
noisy environments
speaker identification
speech processing
speech synthesis
speaker adaptation
speech retrieval