A Multi-modal Soft Targets Approach for Pronunciation Erroneous Tendency Detection.

Ju Lin Wei Zhang Linxuan Wei Yanlu Xie Jinsong Zhang

Published in: ISCSLP (2018)

Keyphrases

multi modal
cross modal
target detection
high dimensional
multi modality
audio visual
false alarms
speech recognition
forward looking infrared
machine learning
wordnet
video search
mean shift
image analysis
image processing
metadata
feature selection