Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling.
Rui LiuYifan HuYi RenXiang YinHaizhou LiPublished in: AAAI (2024)
Keyphrases
- context modeling
- speech synthesis
- context awareness
- speech recognition
- text to speech
- cross modal
- multi modal
- image coder
- arithmetic coding
- multimedia retrieval
- ubiquitous computing
- lossless compression
- facial expressions
- image coding
- context aware
- high quality
- high order
- visual recognition
- bag of features
- ambient intelligence
- subband
- neural network
- image retrieval
- artificial intelligence