Active Learning for Prediction of Prosodic Word Boundaries in Chinese TTS Using Maximum Entropy Markov Model.
Ziping ZhaoXirong MaPublished in: J. Softw. (2013)
Keyphrases
- maximum entropy
- markov model
- markov models
- prosodic features
- active learning
- text to speech
- speech synthesis
- transformation based learning
- markov chain
- maximum entropy principle
- hidden markov models
- statistical model
- conditional random fields
- co occurrence
- semi supervised
- minimum cross entropy
- markov networks
- cost sensitive
- prior information
- learning algorithm
- n gram
- higher order