Effective parameter estimation methods for an ExcitNet model in generative text-to-speech systems.
Ohsung KwonEunwoo SongJae-Min KimHong-Goo KangPublished in: CoRR (2019)
Keyphrases
- parameter estimation
- statistical models
- gibbs sampling
- em algorithm
- parameter values
- random fields
- least squares
- statistical model
- maximum likelihood
- model selection
- markov random field
- parameter estimation algorithm
- experimental data
- text to speech
- maximum likelihood estimation
- approximate inference
- metropolis hastings algorithm
- probabilistic model
- bayesian framework
- closed form
- data mining
- probability distribution
- parameters estimation
- prior knowledge
- high dimensional