Speech Emotion Recognition by Late Fusion of Linguistic and Acoustic Features using Deep Learning Models.
Kiyohide SatoKeita KishiTetsuo KosakaPublished in: APSIPA ASC (2023)
Keyphrases
- learning models
- late fusion
- acoustic features
- visual features
- speech emotion recognition
- machine learning
- image classification
- learning algorithm
- image retrieval
- visual information
- machine learning algorithms
- loss function
- semi supervised learning
- learning tasks
- low level
- keywords
- natural language processing
- natural language
- pattern recognition
- learning problems
- image content
- information retrieval
- decision trees
- key frames
- feature set
- bag of words
- image representation
- training data
- graph cuts