Automatic pronunciation evaluation of foreign speakers using unknown text

In this study we present various techniques to evaluate the pronunciation of students of a foreign language without any knowledge of the uttered text. Previous attempts have shown that it is feasible to evaluate the pronunciation of a non-native speaker by having implicit or explicit knowledge of the uttered text, provided that enough utterances are available. Our approach is to use characteristics of the mother tongue (SOURCE language) of the speaker in the evaluation of his/her pronunciation. We recorded 20 Greek students speaking English (TARGET language) and evaluated their pronunciation using algorithms that include characteristics of the SOURCE language (Greek). We show that the pronunciation scores that are based on both TARGET- and SOURCE-language characteristics have better correlation with the human scores than those based only on characteristics of the TARGET language. As in previous studies, we found that the best-performing algorithms for automatic evaluation of pronunciation are based on speech recognition technology.