Automatic pronunciation scoring of specific phone segments for language instruction

The aim of the work described in this paper is to develop methods for automatically assessing the pronunciation quality of specific phone segments uttered by students learning a foreign language. From the phonetic time alignments generated by SRI's Decipher™ HMM-based speech recognition system, we use various probabilistic models to produce pronunciation scores for the phone utterance. We evaluate the performance of the proposed algorithms by measuring how well the machine-produced scores correlate with human judgments on a large database. Of the various algorithms considered, the one based on phone log-posterior-probability produced the highest correlation (rxy = 0.72) with the human ratings, which was comparable with correlations between human raters.