The UEDIN ASR systems for the IWSLT 2014 evaluation

Peter Bell, Pawel Swietojanski, Joris Driesen, Mark Sinclair, Fergus McInnes, Steve Renals


Abstract
This paper describes the University of Edinburgh (UEDIN) ASR systems for the 2014 IWSLT Evaluation. Notable features of the English system include deep neural network acoustic models in both tandem and hybrid configuration with the use of multi-level adaptive networks, LHUC adaptation and Maxout units. The German system includes lightly supervised training and a new method for dictionary generation. Our voice activity detection system now uses a semi-Markov model to incorporate a prior on utterance lengths. There are improvements of up to 30% relative WER on the tst2013 English test set.
Anthology ID:
2014.iwslt-evaluation.3
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
26–33
Language:
URL:
https://aclanthology.org/2014.iwslt-evaluation.3
DOI:
Bibkey:
Cite (ACL):
Peter Bell, Pawel Swietojanski, Joris Driesen, Mark Sinclair, Fergus McInnes, and Steve Renals. 2014. The UEDIN ASR systems for the IWSLT 2014 evaluation. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 26–33, Lake Tahoe, California.
Cite (Informal):
The UEDIN ASR systems for the IWSLT 2014 evaluation (Bell et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-evaluation.3.pdf