The 2013 KIT IWSLT speech-to-text systems for German and English

Kevin Kilgour, Christian Mohr, Michael Heck, Quoc Bao Nguyen, Van Huy Nguyen, Evgeniy Shin, Igor Tseyzer, Jonas Gehring, Markus Müller, Matthias Sperber, Sebastian Stüker, Alex Waibel


Abstract
This paper describes our English Speech-to-Text (STT) systems for the 2013 IWSLT TED ASR track. The systems consist of multiple subsystems that are combinations of different front-ends, e.g. MVDR-MFCC based and lMel based ones, GMM and NN acoustic models and different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cMLLR.
Anthology ID:
2013.iwslt-evaluation.13
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.13
DOI:
Bibkey:
Cite (ACL):
Kevin Kilgour, Christian Mohr, Michael Heck, Quoc Bao Nguyen, Van Huy Nguyen, Evgeniy Shin, Igor Tseyzer, Jonas Gehring, Markus Müller, Matthias Sperber, Sebastian Stüker, and Alex Waibel. 2013. The 2013 KIT IWSLT speech-to-text systems for German and English. In Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign, Heidelberg, Germany.
Cite (Informal):
The 2013 KIT IWSLT speech-to-text systems for German and English (Kilgour et al., IWSLT 2013)
Copy Citation:
PDF:
https://aclanthology.org/2013.iwslt-evaluation.13.pdf