This paper describes the KIT-NAIST (Contrastive) English speech recognition system for the IWSLT 2012 Evaluation Campaign. In particular, we participated in the ASR track of the IWSLT TED task. The system was developed by Karlsruhe Institute of Technology (KIT) and Nara Institute of Science and Technology (NAIST) teams in collaboration within the interACT project. We employ single system decoding with fully continuous and semi-continuousmodels, as well as a three-stage, multipass system combination framework built with the Janus Recognition Toolkit. On the IWSLT 2010 test set our single system introduced in this work achieves a WER of 17.6%, and our final combination achieves a WER of 14.4%.
Cite as: Heck, M., Kubo, K., Sperber, M., Sakti, S., Stüker, S., Saam, C., Kilgour, K., Mohr, C., Neubig, G., Toda, T., Nakamura, S., Waibel, A. (2012) The KIT-NAIST (contrastive) English ASR system for IWSLT 2012. Proc. International Workshop on Spoken Language Translation (IWSLT 2012), 91-95
@inproceedings{heck12_iwslt,
author={Michael Heck and Keigo Kubo and Matthias Sperber and Sakriani Sakti and Sebastian Stüker and Christian Saam and Kevin Kilgour and Christian Mohr and Graham Neubig and Tomoki Toda and Satoshi Nakamura and Alex Waibel},
title={{The KIT-NAIST (contrastive) English ASR system for IWSLT 2012}},
year=2012,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2012)},
pages={91--95}
}