Applying a hybrid intonation model to a seamless speech synthesizer.
Takashi SaitoMasaharu SakamotoPublished in: INTERSPEECH (2002)
Keyphrases
- probabilistic model
- real time
- neural network
- high level
- process model
- machine learning
- feature selection
- mathematical model
- management system
- computational model
- prediction model
- formal model
- network structure
- statistical model
- maximum likelihood
- prior knowledge
- video sequences
- objective function
- bayesian networks
- similarity measure
- face recognition