Login / Signup
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding.
Sanjana Sankar
Denis Beautemps
Thomas Hueber
Published in:
CoRR (2022)
Keyphrases
</>
neural architectures
feature extractor
pre trained
feature extraction
visual information
neural models
training data
speech recognition
neural network
visual features
training examples
speech signal
feature values
texture descriptors
hidden markov models
control signals
computer vision