Conference paper Open Access

Samsung's System for the IWSLT 2019 End-to-End Speech Translation Task

Potapczyk, Tomasz; Przybysz, Pawel; Chochowski, Marcin; Szumaczuk, Artur

This paper describes the submission to IWSLT 2019 End- to-End speech translation task by Samsung R&D Institute, Poland. We decided to focus on end-to-end English to German TED lectures translation and did not provide any submission for other speech tasks. We used a slightly altered Transformer architecture with standard convolutional layer preparing the audio input to Transformer en- coder. Additionally, we propose an audio segmentation al- gorithm maximizing BLEU score on tst2015 test set.

Files (104.9 kB)
Name Size
IWSLT2019_paper_31.pdf
md5:236e612f3383a1ec298769550370d411 		104.9 kB Download
425
334
views
downloads
All versions This version
Views 425425
Downloads 334334
Data volume 35.0 MB35.0 MB
Unique views 377377
Unique downloads 306306
More info on how stats are collected.
Indexed in
Publication date:
November 2, 2019
DOI:
10.5281/zenodo.3525498

Zenodo DOI Badge

DOI 

10.5281/zenodo.3525498

Markdown 

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3525498.svg)](https://doi.org/10.5281/zenodo.3525498)

reStructedText 

.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.3525498.svg
   :target: https://doi.org/10.5281/zenodo.3525498

HTML 

<a href="https://doi.org/10.5281/zenodo.3525498"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.3525498.svg" alt="DOI"></a>

Image URL 

https://zenodo.org/badge/DOI/10.5281/zenodo.3525498.svg

Target URL 

https://doi.org/10.5281/zenodo.3525498

Communities:
License (for files):
Creative Commons Attribution 4.0 International

Versions

Version 1 10.5281/zenodo.3525498 Nov 2, 2019
Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.3525497. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export