Deep learning for robust feature generation in audiovisual emotion recognition.
Yelin KimHonglak LeeEmily Mower ProvostPublished in: ICASSP (2013)
Keyphrases
- emotion recognition
- deep learning
- feature generation
- audio visual
- facial expressions
- text categorization
- sentiment analysis
- unsupervised learning
- multi modal
- information extraction
- machine learning
- text classification
- word sense disambiguation
- information fusion
- emotional state
- knowledge acquisition
- data sets
- visual information
- natural language
- information retrieval