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: CoRR (2020)
Keyphrases
- cross domain
- speech synthesis
- speech emotion recognition
- facial expressions
- speech recognition
- emotion recognition
- knowledge transfer
- text categorization
- sentiment classification
- transfer learning
- multiple domains
- domain adaptation
- neural network
- machine learning
- semi supervised learning
- text to speech
- case study
- feature selection
- information retrieval
- cross domain learning