CRF-based statistical learning of Japanese accent sandhi for developing Japanese text-to-speech synthesis systems.
Nobuaki MinematsuRyo KuroiwaKeikichi HiroseMichiko WatanabePublished in: SSW (2007)
Keyphrases
- statistical learning
- statistical machine learning
- parameter learning
- text to speech synthesis
- information theory
- model selection
- supervised learning
- artificial intelligence
- multi view face detection
- image analysis
- data sets
- markov random field
- conditional random fields
- pairwise
- feature space
- data analysis
- real world