Our statistical concept-based spoken language translation method consists of three cascaded components: natural language understanding, natural concept generation and natural word generation. In the previous approaches, statistical models are used only in the first two components. In this paper, a novel maximum-entropybased statistical natural word generation algorithm is proposed that takes into account both the word level and concept level context information in the source and the target language. A recursive generation scheme is further devised to integrate this statistical generation algorithm with the previously proposed maximum-entropy-based natural concept generation algorithm. The translation error rate is reduced by 14%-20% in our speech-tospeech translation experiments.
Cite as: Gu, L., Gao, Y. (2005) Use of maximum entropy in natural word generation for statistical concept-based speech-to-speech translation. Proc. Interspeech 2005, 3189-3192, doi: 10.21437/Interspeech.2005-729
@inproceedings{gu05b_interspeech,
author={Liang Gu and Yuqing Gao},
title={{Use of maximum entropy in natural word generation for statistical concept-based speech-to-speech translation}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={3189--3192},
doi={10.21437/Interspeech.2005-729}
}