Utterance-Level Sequential Modeling for Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit.
Tomoki KoriyamaHiroshi SaruwatariPublished in: ICASSP (2020)
Keyphrases
- gaussian process
- speech synthesis
- speech recognition
- gaussian processes
- gaussian process models
- regression model
- model selection
- gaussian process regression
- dynamical models
- latent variables
- approximate inference
- image processing
- dynamical model
- bayesian framework
- hyperparameters
- text to speech
- semi supervised
- gaussian process classification
- covariance function
- higher order
- expectation propagation
- prior knowledge
- learning process
- lower bound
- learning algorithm
- sparse approximations
- neural network