DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models.
Sicheng YangZhiyong WuMinglei LiZhensong ZhangLei HaoWeihong BaoMing ChengLong XiaoPublished in: CoRR (2023)
Keyphrases
- diffusion models
- audio visual
- audio stream
- diffusion model
- multi stream
- broadcast news
- speaker identification
- information diffusion
- audio signals
- emotion recognition
- multimodal interfaces
- text to speech
- gesture recognition
- speech recognition
- social networks
- audio features
- hidden markov models
- viral marketing
- visual information
- speech signal
- automatic transcription
- speech music discrimination
- influence maximization
- hand movements
- human computer interaction