Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation.
Tao TuYuan-Jui ChenAlexander H. LiuHung-yi LeePublished in: CoRR (2020)
Keyphrases
- semi supervised learning
- text to speech synthesis
- semi supervised
- unlabeled data
- labeled data
- text to speech
- speech recognition
- supervised learning
- unsupervised learning
- regularization framework
- active learning
- label propagation
- semi supervised classification
- improve the classification accuracy
- training data
- co training
- graph based semi supervised learning
- machine learning
- automatic speech recognition
- audio visual
- domain adaptation
- transfer learning
- reinforcement learning
- semi supervised learning algorithms
- semi supervised learning methods
- manifold regularization
- speech signal
- labeled and unlabeled data
- learning models
- graph construction
- pairwise
- image segmentation
- decision trees
- clustering algorithm