Factor analyzed voice models for HMM-based speech synthesis.
Kyosuke KazumiYoshihiko NankakuKeiichi TokudaPublished in: ICASSP (2010)
Keyphrases
- speech synthesis
- text to speech
- complex systems
- speech recognition
- statistical model
- experimental data
- multi agent systems
- probabilistic model
- graphical models
- autoregressive
- computational models
- statistical models
- data sets
- hidden markov models
- video sequences
- case study
- genetic algorithm
- model selection
- prior knowledge
- bayesian networks
- bayesian framework
- website
- computer vision
- search engine