Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis.
Makoto TachibanaShinsuke IzawaTakashi NoseTakao KobayashiPublished in: ICASSP (2008)
Keyphrases
- speech synthesis
- computational model
- statistical model
- theoretical framework
- high level
- experimental data
- probabilistic model
- management system
- mathematical model
- prior knowledge
- control strategy
- objective function
- control system
- theoretical analysis
- neural network
- similarity measure
- pattern recognition
- formal model
- text to speech
- adaptation process