A bilevel framework for joint optimization of session compensation and classification for speaker identification.
Chen ChenWei WangYongjun HeJiqing HanPublished in: Digit. Signal Process. (2019)
Keyphrases
- joint optimization
- speaker identification
- classification accuracy
- decision trees
- high level
- sparse representation
- support vector
- pattern recognition
- feature space
- neural network
- feature extraction
- feature selection
- high dimensional
- information retrieval systems
- multi modal
- unsupervised learning
- face recognition
- speech recognition
- image processing