Login / Signup
Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates.
Hendrik Meutzner
Ning Ma
Robert M. Nickel
Christopher Schymura
Dorothea Kolossa
Published in:
ICASSP (2017)
Keyphrases
</>
neural network
visual speech
audio visual speech recognition
multi stream
pattern recognition
hidden markov models
multimedia
visual speech recognition
visual information
acoustic features
audio signal
audio signals
multilayer perceptron
broadcast news
multi modal
video sequences
feature selection