Sequence-to-Sequence Learning for Deep Gaussian Process Based Speech Synthesis Using Self-Attention GP Layer.
Taiki NakamuraTomoki KoriyamaHiroshi SaruwatariPublished in: Interspeech (2021)
Keyphrases
- gaussian process
- speech synthesis
- genetic programming
- learning process
- learning algorithm
- supervised learning
- sparse approximations
- text to speech
- gaussian process regression
- incremental learning
- text mining
- semi supervised
- image processing
- higher order
- speech recognition
- learning tasks
- bayesian framework
- pairwise
- reinforcement learning
- gaussian processes
- information retrieval
- machine learning
- covariance function
- neural network