Improving latency-controlled BLSTM acoustic models for online speech recognition.

Shaofei Xue Zhijie Yan

Published in: ICASSP (2017)

Keyphrases

speech recognition
acoustic models
speaker independent
speech recognizer
hidden markov models
language model
automatic speech recognition
pattern recognition
speech signal
noisy environments
speaker identification
speech recognition systems
neural network
computer vision
multi modal