Fusion of Acoustic and Linguistic Information using Supervised Autoencoder for Improved Emotion Recognition.
Bogdan VlasenkoRaviShankar PrasadMathew Magimai-DossPublished in: MuSe @ ACM Multimedia (2021)
Keyphrases
- emotion recognition
- emotional speech
- linguistic information
- information fusion
- audio visual
- human computer interaction
- emotion classification
- structural information
- semantic information
- data fusion
- linguistic features
- facial expressions
- semi supervised
- sentiment analysis
- machine learning
- emotional state
- affective states
- semantic similarity
- multiword
- part of speech
- image sequences
- multimedia
- information retrieval