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

Tomasz Potapczyk, Pawel Przybysz, Marcin Chochowski, Artur Szumaczuk


Abstract
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.
Anthology ID:
2019.iwslt-1.12
Volume:
Proceedings of the 16th International Conference on Spoken Language Translation
Month:
November 2-3
Year:
2019
Address:
Hong Kong
Editors:
Jan Niehues, Rolando Cattoni, Sebastian Stüker, Matteo Negri, Marco Turchi, Thanh-Le Ha, Elizabeth Salesky, Ramon Sanabria, Loic Barrault, Lucia Specia, Marcello Federico
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
Language:
URL:
https://aclanthology.org/2019.iwslt-1.12
DOI:
Bibkey:
Cite (ACL):
Tomasz Potapczyk, Pawel Przybysz, Marcin Chochowski, and Artur Szumaczuk. 2019. Samsung’s System for the IWSLT 2019 End-to-End Speech Translation Task. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Samsung’s System for the IWSLT 2019 End-to-End Speech Translation Task (Potapczyk et al., IWSLT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2019.iwslt-1.12.pdf
Data
MuST-C