Conference paper Open Access
The IWSLT 2019 KIT Speech Translation System
Pham, Ngoc-Quan; Nguyen, Thai-Son; Ha, Thanh-Le; Hussain, Juan; Schneider, Felix; Niehues, Jan; Stüker, Sebastian; Waibel, Alexander
This paper describes KIT’s submission to the IWSLT 2019 Speech Translation task on two sub-tasks corresponding to two different datasets. We investigate different end-to-end architectures for the speech recognition module, including our new transformer-based architectures. Overall, our modules in the pipe-line are based on the transformer architecture which has recently achieved great results in various fields. In our systems, using transformer is also advantageous compared to traditional hybrid systems in term of simplicity while still having competent results.
| Name | Size | |
|---|---|---|
|
IWSLT2019_paper_40.pdf
md5:c328ea0a9f886839abd3b19cac97b40b |
233.7 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 617 | 617 |
| Downloads | 524 | 524 |
| Data volume | 122.5 MB | 122.5 MB |
| Unique views | 561 | 561 |
| Unique downloads | 478 | 478 |
- Publication date:
- November 2, 2019
- DOI:
-
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International