Rapid speaker adaptation based on D-code extracted from BLSTM-RNN in LVCSR.

Shaofei Xue Zhijie Yan Zhiying Huang Li-Rong Dai

Published in: ISCSLP (2016)

Keyphrases

speaker adaptation
speech recognition
maximum likelihood
automatic speech recognition
recurrent neural networks
nearest neighbor
speech recognizer
speaker dependent
hidden markov models
pattern recognition
neural network
feature space
language model
speech synthesis