Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models.
Danilo de OliveiraNavin Raj PrabhuTimo GerkmannPublished in: CoRR (2023)
Keyphrases
- semantic information
- emotion recognition
- audio visual
- keywords
- semantic analysis
- visual information
- metadata
- wordnet
- semantic features
- human computer interaction
- multi modal
- sentiment analysis
- multimedia
- emotional speech
- artificial intelligence
- facial expressions
- face detection
- information fusion
- semantic similarity
- prior knowledge
- high level
- search engine