The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections Through Federated Learning.
Lillian ZhouYuxin DingMingqing ChenHarry ZhangRohit PrabhavalkarDhruv GulianiGiovanni MottaRajiv MathewsPublished in: ASRU (2023)
Keyphrases
- learning models
- learning algorithm
- learning scheme
- prior knowledge
- reinforcement learning
- learning phase
- learning problems
- online learning
- probability distribution
- learning process
- data sources
- knowledge acquisition
- mathematical model
- user interface
- learning scenarios
- digital libraries
- high quality
- information retrieval