Emotion Controllable Speech Synthesis Using Emotion-Unlabeled Dataset with the Assistance of Cross-Domain Speech Emotion Recognition.
Xiong CaiDongyang DaiZhiyong WuXiang LiJingbei LiHelen MengPublished in: ICASSP (2021)
Keyphrases
- cross domain
- speech synthesis
- speech emotion recognition
- knowledge transfer
- facial expressions
- transfer learning
- speech recognition
- domain adaptation
- sentiment classification
- data sets
- training data
- emotion recognition
- supervised learning
- active learning
- image processing
- cross domain learning
- text categorization
- software engineering
- learning tasks
- pattern recognition
- multiple domains
- decision making
- machine learning