Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech.
Sung-Feng HuangChyi-Jiunn LinDa-Rong LiuYi-Chen ChenHung-yi LeePublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2022)
Keyphrases
- text to speech
- meta learning
- prosodic features
- speech synthesis
- inductive learning
- meta knowledge
- learning tasks
- model selection
- decision trees
- machine learning algorithms
- speech recognition
- base classifiers
- data mining
- metamodel
- word processing
- machine learning
- speaker verification
- feature selection
- data sets
- benchmark datasets
- multi class
- active learning
- bayesian networks