| Paper ID | SPE-P20.5 |
| Paper Title |
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation |
| Authors |
Thai Son Nguyen, Sebastian Stueker, Karlsruhe Institute of Technology, Germany; Jan Niehues, Maastricht University, Netherlands; Alex Waibel, Karlsruhe Institute of Technology, Germany |
| Session | SPE-P20: Speech Recognition: Acoustic Modelling II |
| Location | On-Demand |
| Session Time: | Friday, 08 May, 11:45 - 13:45 |
| Presentation Time: | Friday, 08 May, 11:45 - 13:45 |
| 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 |