Combining Active and Semi-Supervised Learning for Homograph Disambiguation in Mandarin Text-to-Speech Synthesis.
Binbin ShenZhiyong WuYongxin WangLianhong CaiPublished in: INTERSPEECH (2011)
Keyphrases
- face recognition
- semi supervised learning
- text to speech synthesis
- semi supervised
- labeled data
- unlabeled data
- unsupervised learning
- semi supervised classification
- supervised learning
- label propagation
- machine learning
- manifold regularization
- semi supervised learning methods
- training data
- co training
- improve the classification accuracy
- learning models
- co occurrence
- graph based semi supervised learning
- labeled examples
- transfer learning
- computer vision
- active learning
- word sense disambiguation
- text classification
- text to speech
- natural language processing
- regularization framework
- text mining
- natural language
- pattern recognition