Picture for Jiabin Xue

Jiabin Xue

Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation

Add code
Jun 27, 2023
Viaarxiv icon

A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition

Add code
Apr 17, 2019
Figure 1 for A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Figure 2 for A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Figure 3 for A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Figure 4 for A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Viaarxiv icon

Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition

Add code
Apr 17, 2019
Figure 1 for Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition
Figure 2 for Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition
Figure 3 for Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition
Figure 4 for Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition
Viaarxiv icon