Demonstration of an HMM-based photorealistic expressive audio-visual speech synthesis system.
Panagiotis Paraskevas FilntisisAthanasios KatsamanisPetros MaragosPublished in: ICIP (2017)
Keyphrases
- audio visual
- speech synthesis
- photorealistic
- speech recognition
- hidden markov models
- computer graphics
- multi modal
- hand held
- virtual reality
- image space
- visual information
- text to speech
- range images
- highly accurate
- complex scenes
- d scene
- image acquisition
- vision system
- visual data
- point cloud
- emotion recognition
- multi stream
- speaker verification
- multimedia
- dynamic scenes
- information retrieval
- computer vision
- visual features
- human computer interaction
- machine learning
- image content