Text-to-Visual Speech Synthesis for General Objects Using Parameter-Based Lip Models.
Ze-Jing ChuangChung-Hsien WuPublished in: IEEE Pacific Rim Conference on Multimedia (2002)
Keyphrases
- speech synthesis
- probabilistic model
- visual objects
- text to speech
- information retrieval
- keywords
- moving objects
- special case
- database
- speech recognition
- bounding box
- object models
- model selection
- semantic labels
- visual tasks
- human machine interaction
- linear model
- visual information
- low level
- image processing
- computer vision
- machine learning
- neural network