| Knowledge Distillation from Multi-Modality to Single-Modality for Person Verification. | 0 | 0.34 | 2021 |
| Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition. | 0 | 0.34 | 2021 |
| Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party. | 1 | 0.36 | 2021 |
