EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation.
Xingqun QiChen LiuLincheng LiJie HouHaoran XinXin YuPublished in: CoRR (2023)
Keyphrases
- emotion recognition
- audio visual
- audio stream
- broadcast news
- multi stream
- audio signals
- emotional state
- text to speech
- multi modal
- speaker identification
- hand movements
- wide variety
- cepstral features
- audio recordings
- multimodal interfaces
- audio features
- gesture recognition
- speech recognition
- human computer interaction
- automatic transcription
- digital audio
- multimedia
- hidden markov models
- speech music discrimination
- facial expressions
- speech processing
- hand gestures
- audio video
- recognition engine
- signal processing
- language acquisition
- visual information
- generation process
- human language
- data driven
- visual data
- prosodic features
- speech signal
- spoken documents
- sign language
- linear predictive coding
- real world