Measuring the Capability of a Speech Translation System
暂无分享,去创建一个
This chapter introduces an evaluation method for speech translation systems. Since the method estimates the system’s capability in a commonly known English proficiency measurement score such as TOEIC, the evaluation results are very comprehensible not only for researchers but also for system users. This chapter also formulates the evaluation errors and discusses the costs necessary for evaluation. Lastly, we provide a solution to the evaluation cost issue by applying an automatic evaluation method.
[1] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.
[2] Hitoshi Iida,et al. A speech and language database for speech translation research , 1994, ICSLP.
[3] Eiichiro Sumita,et al. Solutions to Problems Inherent in Spoken-language Translation: The ATR-MATRIX Approach , 1999 .
[4] Yoshinori Sagisaka,et al. Evaluation of the ATR-matrix speech translation system with a pair comparison method between the system and humans , 2000, INTERSPEECH.