Description of the UEDIN system for German ASR

Joris Driesen, Peter Bell, Mark Sinclair, Steve Renals


Abstract
In this paper we describe the ASR system for German built at the University of Edinburgh (UEDIN) for the 2013 IWSLT evaluation campaign. For ASR, the major challenge to overcome, was to find suitable acoustic training data. Due to the lack of expertly transcribed acoustic speech data for German, acoustic model training had to be performed on publicly available data crawled from the internet. For evaluation, lack of a manual segmentation into utterances was handled in two different ways: by generating an automatic segmentation, and by treating entire input files as a single segment. Demonstrating the latter method is superior in the current task, we obtained a WER of 28.16% on the dev set and 36.21% on the test set.
Anthology ID:
2013.iwslt-evaluation.11
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.11
DOI:
Bibkey:
Cite (ACL):
Joris Driesen, Peter Bell, Mark Sinclair, and Steve Renals. 2013. Description of the UEDIN system for German ASR. In Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign, Heidelberg, Germany.
Cite (Informal):
Description of the UEDIN system for German ASR (Driesen et al., IWSLT 2013)
Copy Citation:
PDF:
https://aclanthology.org/2013.iwslt-evaluation.11.pdf