Learning Adaptive Downsampling Encoding for Online End-to-End Speech Recognition.

Rui Na Junfeng Hou Wu Guo Yan Song Lirong Dai

Published in: APSIPA (2019)

Keyphrases

end to end
speech recognition
pattern recognition
noisy environments
neural network
image processing
hidden markov models
language model
speech signal
automatic speech recognition
scalable video
congestion control
speech synthesis
speech processing