Optimized photorealistic audiovisual speech synthesis using active appearance modeling.
Wesley MattheysesLukas LataczWerner VerhelstPublished in: AVSP (2010)
Keyphrases
- photorealistic
- speech synthesis
- appearance modeling
- speech recognition
- hand held
- computer graphics
- d scene
- highly accurate
- text to speech
- virtual reality
- complex scenes
- range images
- appearance model
- object tracking
- image space
- visual tracking
- image acquisition
- vision system
- point cloud
- motion estimation
- nearest neighbor
- metric learning
- real time
- image processing
- mean shift
- object detection
- hidden markov models
- pairwise
- object recognition
- image sequences