C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Synthesising visual speech using dynamic visemes and deep learning architectures.
Ausdang Thangthai
Ben Milner
Sarah Taylor
Published in:
Comput. Speech Lang. (2019)
Keyphrases
</>
deep learning
visual speech
visual speech recognition
hidden markov models
machine learning
unsupervised learning
lip reading
noisy environments
image processing
weakly supervised
feature space
speech signal
speaker identification