Multimodal Fusion of Speech and Text using Semi-supervised LDA for Indexing Lecture Videos.
Moula HusainS. M. MeenaPublished in: NCC (2019)
Keyphrases
- lecture videos
- semi supervised
- multimodal fusion
- audio visual
- keywords
- multimodal interfaces
- multimedia
- user experience
- hybrid learning
- learning objects
- visual cues
- learning materials
- video segments
- distance learning
- face recognition
- high definition
- visual information
- multi modal
- high robustness
- text to speech
- human computer interaction
- multimodal interaction
- text mining
- principal component analysis
- feature extraction
- semantic content
- video analysis
- gesture recognition
- information retrieval
- natural language processing
- user interaction
- learning process
- visual data
- video clips
- dimensionality reduction
- search engine