The UEDIN English ASR system for the IWSLT 2013 evaluation

Peter Bell, Fergus McInnes, Siva Reddy Gangireddy, Mark Sinclair, Alexandra Birch, Steve Renals


Abstract
This paper describes the University of Edinburgh (UEDIN) English ASR system for the IWSLT 2013 Evaluation. Notable features of the system include deep neural network acoustic models in both tandem and hybrid configuration, cross-domain adaptation with multi-level adaptive networks, and the use of a recurrent neural network language model. Improvements to our system since the 2012 evaluation – which include the use of a significantly improved n-gram language model – result in a 19% relative WER reduction on the tst2012 set.
Anthology ID:
2013.iwslt-evaluation.22
Volume:
Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 5-6
Year:
2013
Address:
Heidelberg, Germany
Editor:
Joy Ying Zhang
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2013.iwslt-evaluation.22
DOI:
Bibkey:
Cite (ACL):
Peter Bell, Fergus McInnes, Siva Reddy Gangireddy, Mark Sinclair, Alexandra Birch, and Steve Renals. 2013. The UEDIN English ASR system for the IWSLT 2013 evaluation. In Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign, Heidelberg, Germany.
Cite (Informal):
The UEDIN English ASR system for the IWSLT 2013 evaluation (Bell et al., IWSLT 2013)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/2013.iwslt-evaluation.22.pdf