Automatic detection and correction of non-native English pronunciations

Improving the feedback quality of a computer-based system for pronunciation training requires rather detailed and precise knowledge about the place and the nature of actual mispronunciations in a student’s utterance. To be able to provide this kind of information, components for the automatic localizat ion and correction of pronunciation errors have been developed. This work was part of a project aimed a t integrating state-of-the-art speech recognition technology into a pronunciation training environmen t for adult, intermediate level learners. Although th e technologies described here are in principle valid for any language pairs, the current system focuses on I talian and German learners of English.