Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis.
Weiqin LiShun LeiQiaochu HuangYixuan ZhouZhiyong WuShiyin KangHelen MengPublished in: INTERSPEECH (2023)
Keyphrases
- semi supervised
- text to speech synthesis
- supervised learning
- restricted boltzmann machine
- multi view
- training process
- training samples
- pairwise
- fully labeled
- conversational speech
- text to speech
- training phase
- labeled data
- multi modal
- active learning
- training examples
- test set
- speech recognition
- unlabeled data
- semi supervised learning
- modeling method
- semi supervised clustering
- batch mode
- online learning
- natural language