A targets-based superpositional model of fundamental frequency contours applied to HMM-based speech synthesis.
Jinfu NiYoshinori ShigaChiori HoriYutaka KidawaraPublished in: INTERSPEECH (2013)
Keyphrases
- statistical model
- high level
- probability distribution
- speech synthesis
- computational model
- parameter estimation
- hidden markov models
- probabilistic model
- prior knowledge
- pattern recognition
- learning algorithm
- management system
- theoretical analysis
- theoretical framework
- mathematical model
- computer vision
- social networks