Focus-attention-enhanced Crossmodal Transformer with Metric Learning for Multimodal Speech Emotion Recognition.
Keulbit KimNamhyun ChoPublished in: INTERSPEECH (2023)
Keyphrases
- metric learning
- speech emotion recognition
- distance metric
- distance metric learning
- person re identification
- distance function
- machine learning and pattern recognition
- pairwise
- multi task
- nearest neighbor classification
- semi supervised
- learning tasks
- mahalanobis metric
- semi supervised clustering
- feature space
- data sets
- dimensionality reduction
- image processing
- learning algorithm
- machine learning
- semi supervised learning
- neural network
- domain knowledge
- active learning
- computer vision
- semi definite programming
- margin maximization
- maximum variance unfolding