| Paper ID | SPE-P6.10 |
| Paper Title |
Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks |
| Authors |
Andros Tjandra, Nara Institute of Science and Technology, Japan; Chunxi Liu, Frank Zhang, Xiaohui Zhang, Yongqiang Wang, Gabriel Synnaeve, Facebook AI, United States; Satoshi Nakamura, Nara Institute of Science and Technology, Japan; Geoffrey Zweig, Facebook AI, United States |
| Session | SPE-P6: Speech Recognition: Acoustic Modelling I |
| Location | On-Demand |
| Session Time: | Wednesday, 06 May, 09:00 - 11:00 |
| Presentation Time: | Wednesday, 06 May, 09:00 - 11:00 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-RECO] Acoustic Modeling for Automatic Speech Recognition |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |