Asynchronous integration of visual information in an automatic speech recognition system.
Mamoun AlissaliPaul DelégliseAlexandrina RogozanPublished in: ICSLP (1996)
Keyphrases
- visual information
- automatic annotation
- visual features
- low level
- visual content
- visual cues
- audio visual
- image collections
- visual information retrieval
- human visual system
- visual data
- textual information
- databases
- eye movements
- low level features
- visual scene
- visual input
- content based image
- image content
- semantic information
- image classification
- image processing
- content based image retrieval systems
- computer vision