Mongolian emotional speech synthesis based on transfer learning and emotional embedding.
Aihong HuangFeilong BaoGuanglai GaoYu ShanRui LiuPublished in: IALP (2021)
Keyphrases
- transfer learning
- speech synthesis
- knowledge transfer
- learning tasks
- cross domain
- reinforcement learning
- manifold alignment
- speech recognition
- text to speech
- active learning
- text classification
- labeled data
- semi supervised learning
- machine learning
- multi task learning
- multi task
- data distribution
- machine learning algorithms
- domain adaptation
- emotion recognition
- pattern recognition
- learning algorithm
- vocal tract
- data mining
- collaborative filtering
- semi supervised
- target domain
- data points