Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding.
Sanjana SankarDenis BeautempsFrédéric EliseiOlivier PerrotinThomas HueberPublished in: INTERSPEECH (2023)
Keyphrases
- lip reading
- speech recognition
- head tracking
- finite state transducers
- recognition engine
- speech signal
- speaker identification
- visual speech
- autistic children
- hand movements
- speech synthesis
- test set
- expression recognition
- decoding algorithm
- emotion recognition
- audio visual
- decoding process
- class distribution
- dynamic model
- visual attention
- dynamical systems
- video sequences