Age-Invariant Training for End-to-End Child Speech Recognition Using Adversarial Multi-Task Learning.
Lars RumbergHanna EhlertUlrike LüdtkeJörn OstermannPublished in: Interspeech (2021)
Keyphrases
- end to end
- multi task learning
- multi task
- learning tasks
- gaussian processes
- multiple tasks
- learning problems
- high order
- multi label image annotation
- multitask learning
- congestion control
- supervised learning
- training set
- learning models
- transfer learning
- learning process
- theoretical analysis
- hidden markov models
- feature vectors