This paper describes our recent work on integrating speech recognition and machine translation for improving speech translation performance. Two approaches are applied and their performance are evaluated in the workshop of IWSLT 2005. The first is direct N-best hypothesis translation, and the second, a pseudo-lattice decoding algorithm for translating word lattice, can dramatically reduce computation cost incurred by the first approach. We found in the experiments that both of these approaches could improve speech translation significantly.
Cite as: Zhang, R., Kikui, G., Yamamoto, H. (2005) Using multiple recognition hypotheses to improve speech translation. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 30-36
@inproceedings{zhang05b_iwslt,
author={Ruiqiang Zhang and Genichiro Kikui and Hirofumi Yamamoto},
title={{Using multiple recognition hypotheses to improve speech translation}},
year=2005,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)},
pages={30--36}
}