AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis.
Hendric VoßStefan KoppPublished in: CoRR (2023)
Keyphrases
- multimodal interfaces
- hand movements
- speech recognition
- gesture recognition
- multi stream
- speech signal
- audio visual
- spatio temporal
- human computer interaction
- inductive learning
- facial animation
- concept learning
- speech synthesis
- sign language
- fuzzy logic
- hidden markov models
- temporal information
- power system
- recognition engine
- texture synthesis
- learning mechanism
- endpoint detection
- power transformers
- text to speech
- hearing impaired
- continuous stream
- program synthesis
- multimodal interaction
- constructive induction
- dct coefficients
- automatic speech recognition
- hand gestures
- human communication
- input device
- dialogue system
- fault diagnosis
- multi modal
- user interface
- video sequences