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:
ICASSP (2022)
Keyphrases
</>
neural architectures
feature extractor
pre trained
neural models
neural network
feature extraction
speech recognition
visual information
training data
visual features
training examples
control signals
feature values
learning algorithm
recognition scheme
texture descriptors
speech signal
neural network model