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