Non-negative intermediate-layer DNN adaptation for a 10-KB speaker adaptation profile.

Kshitiz Kumar Chaojun Liu Yifan Gong

Published in: ICASSP (2016)

Keyphrases

speaker adaptation
speech recognition
maximum likelihood
automatic speech recognition
knowledge base
speech recognizer
pattern recognition
training process
speaker independent
language model
natural language processing
information retrieval systems
text classification
em algorithm
speech signal
speech synthesis