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.

Files (233.7 kB)
Name Size
IWSLT2019_paper_40.pdf
md5:c328ea0a9f886839abd3b19cac97b40b
233.7 kB Download
346
379
views
downloads
All versions This version
Views 346346
Downloads 379379
Data volume 88.6 MB88.6 MB
Unique views 302302
Unique downloads 340340

Share

Cite as