EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis.
Haobin TangXulong ZhangJianzong WangNing ChengJing XiaoPublished in: CoRR (2023)
Keyphrases
- speech synthesis
- diffusion models
- emotional state
- emotion recognition
- speech recognition
- diffusion model
- information diffusion
- affective computing
- text to speech
- human decision making
- facial expressions
- social networks
- affective states
- vocal tract
- viral marketing
- prosodic features
- influence maximization
- information flow
- social interaction
- steady state
- dynamic programming
- information retrieval
- machine learning