Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction.
David QiuYanzhang HeQiujia LiYu ZhangLiangliang CaoIan McGrawPublished in: Interspeech (2021)
Keyphrases
- end to end
- multi task learning
- multi task
- speech recognition
- learning tasks
- multiple tasks
- multitask learning
- gaussian processes
- learning problems
- multi label image annotation
- theoretical analysis
- transfer learning
- high order
- learning models
- congestion control
- automatic speech recognition
- metric learning
- learning algorithm
- inductive learning
- feature selection