Decoupled Pronunciation and Prosody Modeling in Meta-Learning-based Multilingual Speech Synthesis.
Yukun PengZhenhua LingPublished in: INTERSPEECH (2022)
Keyphrases
- speech synthesis
- speech recognition
- meta learning
- text to speech
- prosodic features
- machine learning algorithms
- hidden markov models
- learning tasks
- inductive learning
- model selection
- pattern recognition
- machine learning
- language model
- metamodel
- decision trees
- spontaneous speech
- speech signal
- automatic speech recognition
- feature selection
- data mining
- feature extraction