Paper: A Unified Approach In Speech-To-Speech Translation: Integrating Features Of Speech Recognition And Machine Translation

ACL ID C04-1168
Title A Unified Approach In Speech-To-Speech Translation: Integrating Features Of Speech Recognition And Machine Translation
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2004
Authors

Based upon a statistically trained speech translation system, in this study, we try to combine distinctive features derived from the two modules: speech recognition and statistical machine translation, in a log- linear model. The translation hypotheses are then rescored and translation perfor- mance is improved. The standard trans- lation evaluation metrics, including BLEU, NIST, multiple reference word error rate and its position independent counterpart, were optimized to solve the weights of the features in the log-linear model. The exper- imental results have shown signi cant im- provement over the baseline IBM model 4 in all automatic translation evaluation met- rics. The largest was for BLEU, by 7.9% absolute.