Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings.
Tenglong AoQingzhe GaoYuke LouBaoquan ChenLibin LiuPublished in: CoRR (2022)
Keyphrases
- multimodal interfaces
- network architecture
- speech recognition
- hand movements
- gesture recognition
- vector space
- multi stream
- neural network
- audio visual
- hierarchical structure
- manifold learning
- speech signal
- bio inspired
- automatic speech recognition
- dimensionality reduction
- high dimensional data
- data sets
- low dimensional
- texture synthesis
- speech synthesis
- hidden markov models
- text to speech
- endpoint detection
- facial animation
- emotion recognition
- noisy environments
- human computer interaction
- hierarchical clustering