AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis.
Hendric VoßStefan KoppPublished in: ICMI (2023)
Keyphrases
- multimodal interfaces
- hand movements
- speech recognition
- gesture recognition
- facial animation
- spatio temporal
- human computer interaction
- hidden markov models
- speech signal
- multi stream
- fuzzy logic
- audio visual
- concept learning
- inductive learning
- hand gestures
- temporal information
- speech synthesis
- automatic speech recognition
- multimodal interaction
- constructive induction
- recognition engine
- texture synthesis
- sign language
- continuous stream
- language acquisition
- text to speech
- genetic algorithm
- speaker identification
- broadcast news
- spoken language
- dct coefficients
- fault diagnosis
- multi modal
- distribution network
- emotion recognition
- program synthesis
- power system
- spontaneous speech
- decision trees
- machine learning
- partial discharge