The AFRL IWSLT 2020 Systems: Work-From-Home Edition

Brian Ore, Eric Hansen, Tim Anderson, Jeremy Gwinnup


Abstract
This report summarizes the Air Force Research Laboratory (AFRL) submission to the offline spoken language translation (SLT) task as part of the IWSLT 2020 evaluation campaign. As in previous years, we chose to adopt the cascade approach of using separate systems to perform speech activity detection, automatic speech recognition, sentence segmentation, and machine translation. All systems were neural based, including a fully-connected neural network for speech activity detection, a Kaldi factorized time delay neural network with recurrent neural network (RNN) language model rescoring for speech recognition, a bidirectional RNN with attention mechanism for sentence segmentation, and transformer networks trained with OpenNMT and Marian for machine translation. Our primary submission yielded BLEU scores of 21.28 on tst2019 and 23.33 on tst2020.
Anthology ID:
2020.iwslt-1.11
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | IWSLT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
103–108
Language:
URL:
https://www.aclweb.org/anthology/2020.iwslt-1.11
DOI:
10.18653/v1/2020.iwslt-1.11
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwslt-1.11.pdf
Video:
 http://slideslive.com/38929615