International Workshop on Spoken Language Translation (IWSLT) 2011

San Francisco, CA, USA
December 8-9, 2011

Speech Recognition for Machine Translation in Quaero

Lori Lamel (1), Sandrine Courcinous (4), Julien Despres (4), Jean-Luc Gauvain (1), Yvan Josse (4), Kevin Kilgour (2), Florian Kraft (2), Viet Bac Le (1,4), Hermann Ney (3), Markus Nußbaum-Thom (3), Ilya Oparin (1), Tim Schlippe (2), Ralf Schlüter (3), Tanja Schultz (2), Thiago Fraga da Silva (1), Sebastian Stüker (2), Martin Sundermeyer (3), Bianca Vieru (4), Ngoc Thang Vu (2), Alex Waibel (2), Cècile Woehrling (4)

(1) CNRS-LIMSI, Orsay, France
(2) Karlsruhe Institute of Technology, Karlsruhe, Germany
(3) RWTH Aachen University, Aachen, Germany
(4) Vocapia Research, Orsay, France

This paper describes the speech-to-text systems used to provide automatic transcriptions used in the Quaero 2010 evaluation of Machine Translation from speech. Quaero ( is a large research and industrial innovation program focusing on technologies for automatic analysis and classification of multimedia and multilingual documents. The ASR transcript is the result of a Rover combination of systems from three teams ( KIT, RWTH, LIMSI+VR) for the French and German languages. The casesensitive word error rates (WER) of the combined systems were respectively 20.8% and 18.1% on the 2010 evaluation data, relative WER reductions of 14.6% and 17.4% respectively over the best component system.

Full Paper

Bibliographic reference.  Lamel, Lori / Courcinous, Sandrine / Despres, Julien / Gauvain, Jean-Luc / Josse, Yvan / Kilgour, Kevin / Kraft, Florian / Le, Viet Bac / Ney, Hermann / Nußbaum-Thom, Markus / Oparin, Ilya / Schlippe, Tim / Schlüter, Ralf / Schultz, Tanja / Fraga da Silva, Thiago / Stüker, Sebastian / Sundermeyer, Martin / Vieru, Bianca / Vu, Ngoc Thang / Waibel, Alex / Woehrling, Cècile (2011): "Speech recognition for machine translation in Quaero", In IWSLT-2011, 121-128.