Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection.

Danni Liu Gerasimos Spanakis Jan Niehues

Published in: CoRR (2020)

Keyphrases

speech recognition
low latency
pattern recognition
hidden markov models
noisy environments
language model
machine translation
high throughput
speech signal
speech synthesis
real time
information retrieval
computer vision
maximum likelihood
speaker identification
speech recognizer