Efficient Learning of Articulatory Models Based on Multi-Label Training and Label Correction for Pronunciation Learning.
Richeng DuanTatsuya KawaharaMasatake DantsujiHiroaki NanjoPublished in: ICASSP (2018)
Keyphrases
- multi label
- efficient learning
- structured prediction
- multi label learning
- max margin
- learning tasks
- multi label classification
- learning algorithm
- graph cuts
- multi instance
- image classification
- text categorization
- unsupervised learning
- prior knowledge
- text classification
- supervised learning
- feature selection
- image annotation
- binary classification
- conditional random fields
- learning problems
- class labels
- training set
- neural network
- speech recognition
- active learning
- label space
- single label classification