Active learning for the prediction of prosodic phrase boundaries in Chinese speech synthesis systems using conditional random fields.
Ziping ZhaoXirong MaPublished in: SNPD (2015)
Keyphrases
- speech synthesis
- speech recognition
- active learning
- prosodic features
- text to speech
- management system
- complex systems
- bayesian networks
- vocal tract
- prediction accuracy
- distributed systems
- language model
- supervised learning
- relevance feedback
- learning process
- pairwise
- pattern recognition
- neural network
- speech corpus
- text to speech synthesis