Fusion of audio and video data by neural networks for robust vowel recognition.
Kristian KroschelM. S. MekhaielFrédéric BerthommierPublished in: ECC (1999)
Keyphrases
- video data
- neural network
- multimedia
- digital video
- visual data
- video analysis
- vowel recognition
- video streams
- multimodal information
- video sequences
- video recordings
- video content
- video database
- video frames
- surveillance videos
- video retrieval
- video camera
- pattern recognition
- temporal structure
- video indexing
- video clips
- pattern classification
- video shots
- content based video retrieval
- multimedia systems
- audio visual
- machine learning
- video annotation
- content based indexing
- video browsing
- video scene
- k nearest neighbor
- video abstraction
- visual information
- video dataset
- soccer video
- face recognition
- key frames
- databases