Login / Signup
Integration of deep bottleneck features for audio-visual speech recognition.
Hiroshi Ninomiya
Norihide Kitaoka
Satoshi Tamura
Yurie Iribe
Kazuya Takeda
Published in:
INTERSPEECH (2015)
Keyphrases
</>
audio visual speech recognition
feature space
feature vectors
low level
feature set
feature extraction
high dimensional
multiresolution
multi stream