INTERSPEECH 2006 - ICSLP
We discuss how to measure the reliability of recognized utterances based on a confidence measure, and applied it to a dialog speech translation system. In this study, we employ generalized word posterior probability (GWPP), a confidence measure for verifying recognized words, and expand it to measure the reliability of recognized utterances. We confirmed the performance improvement by applying the rejection technique to a dialog speech translation system from Japanese to English. We conducted two kinds of performance evaluation. One is a ranking evaluation of translation output by human evaluators. The other is to measure the machine output against human results by a paired-comparison method. Both of them yield significant improvements.
Bibliographic reference. Takezawa, Toshiyuki / Shimizu, Tohru (2006): "Performance improvement of dialog speech translation by rejecting unreliable utterances", In INTERSPEECH-2006, paper 1100-Tue2CaP.6.