Project Name
Data Representation and Learning for Dialogue System (II)
Project Goal
- Enabling conversational AI in heterogeneous environments, building virtual agents or assistants for smart campus and hospital, enhancing deep learning theories, and facilitating explainable AI
- Enriching and integrating dialog agent, speech recognition, natural language understanding and generation
Project Description
1. Statistic Explainable Deep Model
＊Spoken dialogue system
＊Online speech recognition
2. Efficient Adaptation Learning
＊Efficient accent adaptation
＊Attention guided code-switching speech recognition
3. Data Efficient Dialogue Policy Learning
＊Causal confusion reduction in imitation learning
＊Guidance learning with corrective feedback
4. Reliable Dialogue System
＊Learning to generate safe responses
＊Robust dialogue system
