Photorealistic 2D audiovisual text-to-speech synthesis using active appearance models.
Wesley MattheysesWerner VerhelstPublished in: FAA (2010)
Keyphrases
- photorealistic
- text to speech synthesis
- virtual reality
- computer graphics
- highly accurate
- d scene
- range images
- hand held
- text to speech
- image space
- complex scenes
- texture mapping
- image acquisition
- point cloud
- facial expression synthesis
- vision system
- image based rendering
- virtual environment
- viewpoint
- dynamic scenes
- frame rate
- photorealistic rendering
- real time
- multi view
- high speed
- high accuracy
- three dimensional
- machine learning