A unified approach in speech-to-speech translation
Ruiqiang Zhang, Genichiro Kikui, Hirofumi Yamamoto, Taro Watanabe, Frank K. Soong, Wai-Kit Lo · 2004
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 loglinear model. The translation hypotheses are then rescored and translation performance is improved. The standard translation 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 experimental results have shown significant improvement over the baseline IBM model 4 in all automatic translation evaluation metrics. The largest was for BLEU, by 7.9% absolute.