Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling.
Rui LiuYifan HuYi RenXiang YinHaizhou LiPublished in: CoRR (2023)
Keyphrases
- speech synthesis
- context modeling
- context awareness
- speech recognition
- cross modal
- multi modal
- text to speech
- image coder
- high order
- lossless compression
- multimedia retrieval
- context aware
- facial expressions
- bag of features
- high quality
- neural network
- ubiquitous computing
- subband
- hidden markov models
- visual recognition
- natural language
- smart home
- arithmetic coding
- entropy coding
- image processing