Code-Switching Speech Synthesis Based on Self-Supervised Learning and Domain Adaptive Speaker Encoder.
Yi-Xing LinCheng-Hsun PaiPhuong Thi LeBima PrihastoChien-Ling HuangJia-Ching WangPublished in: ICASSP (2023)
Keyphrases
- speech synthesis
- speech recognition
- learning process
- learning systems
- learning algorithm
- domain independent
- vocal tract
- learning tasks
- active learning
- reinforcement learning
- prior knowledge
- knowledge acquisition
- online learning
- supervised learning
- learning capabilities
- motion estimation
- domain specific
- low complexity
- adaptive learning
- adaptive control
- complex domains
- machine learning