International Workshop on Spoken Language Translation (IWSLT) 2012

Hong Kong
December 6-7, 2012

The KIT-NAIST (Contrastive) English ASR System for IWSLT 2012

Michael Heck (1), Keigo Kubo (2), Matthias Sperber (1), Sakriani Sakti (2), Sebastian Stüker (1), Christian Saam (1), Kevin Kilgour (1), Christian Mohr (1), Graham Neubig (2), Tomoki Toda (2), Satoshi Nakamura (2), Alex Waibel (1)

(1) Institute for Anthropomatics, Karlsruhe Institute of Technology, Germany
(2) Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Japan

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%.

Full Paper   

Bibliographic reference.  Heck, Michael / Kubo, Keigo / Sperber, Matthias / Sakti, Sakriani / Stüker, Sebastian / Saam, Christian / Kilgour, Kevin / Mohr, Christian / Neubig, Graham / Toda, Tomoki / Nakamura, Satoshi / Waibel, Alex (2012): "The KIT-NAIST (contrastive) English ASR system for IWSLT 2012", In IWSLT-2012, 91-95.