Ng, R.W.M., Doulaty, M., Doddipatla, R. et al. (7 more authors) (2014) The USFD SLT System for IWSLT 2014. In: Federico, M., Stücker, S. and Yvon, F., (eds.) Proceedings of the International Workshop on Spoken Language Translation. 11th International Workshop on Spoken Language Translation, 04-05 Dec 2014, Lake Tahoe, California (USA). IWSLT , http://workshop2014.iwslt.org/64.php
Abstract
The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by two multi-pass deep neural network systems with adaptation and rescoring techniques. Machine translation (MT) is achieved by a phrase-based system. The USFD primary system incorporates state-of-the-art ASR and MT techniques and gives a BLEU score of 23.45 and 14.75 on the English-to-French and English-to-German speech-to- text translation task with the IWSLT 2014 data. The USFD contrastive systems explore the integration of ASR and MT by using a quality estimation system to rescore the ASR out- puts, optimising towards better translation. This gives a fur- ther 0.54 and 0.26 BLEU improvement respectively on the IWSLT 2012 and 2014 evaluation data.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2014 IWSLT/The Author(s). Reproduced in accordance with the publisher's self-archiving policy. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Oct 2015 15:46 |
Last Modified: | 19 Dec 2022 13:31 |
Published Version: | http://workshop2014.iwslt.org/downloads/proceeding... |
Status: | Published |
Publisher: | IWSLT |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:86701 |