KIT’s IWSLT 2018 SLT Translation System

Matthias Sperber, Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues, Markus Müller, Thanh-Le Ha, Sebastian Stüker, Alex Waibel


Abstract
This paper describes KIT’s submission to the IWSLT 2018 Translation task. We describe a system participating in the baseline condition and a system participating in the end-to-end condition. The baseline system is a cascade of an ASR system, a system to segment the ASR output and a neural machine translation system. We investigate the combination of different ASR systems. For the segmentation and machine translation components, we focused on transformer-based architectures.
Anthology ID:
2018.iwslt-1.19
Volume:
Proceedings of the 15th International Conference on Spoken Language Translation
Month:
October 29-30
Year:
2018
Address:
Brussels
Editors:
Marco Turchi, Jan Niehues, Marcello Frederico
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Conference on Spoken Language Translation
Note:
Pages:
131–135
Language:
URL:
https://aclanthology.org/2018.iwslt-1.19
DOI:
Bibkey:
Cite (ACL):
Matthias Sperber, Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues, Markus Müller, Thanh-Le Ha, Sebastian Stüker, and Alex Waibel. 2018. KIT’s IWSLT 2018 SLT Translation System. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 131–135, Brussels. International Conference on Spoken Language Translation.
Cite (Informal):
KIT’s IWSLT 2018 SLT Translation System (Sperber et al., IWSLT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.iwslt-1.19.pdf