Investigation of Modeling Units for Mandarin Speech Recognition Using Dfsmn-ctc-smbr.

Shiliang Zhang Ming Lei Yuan Liu Wei Li

Published in: ICASSP (2019)

Keyphrases

speech recognition
speech signal
automatic speech recognition
language model
audio visual
modeling method
emotion recognition
spoken document retrieval
genetic algorithm
pattern recognition
petri net
class distribution
modeling language
vocal tract
prosodic features