Speaker-based accented English clustering using a world English archive

English is the only language available for global communication. Due to the influence of speakers’ mother tongue, however, those from different regions often have different accents in their pronunciation of English. The ultimate goal of our project is automatic creation of a global pronunciation map of World Englishes on an individual basis, for speakers to use to locate similar English pronunciations. Creating the map mathematically requires a matrix of pronunciation distances among all the speakers considered. Our previous study proposed a good algorithm for that purpose [1], where, using phonetic reference pronunciation distances calculated from labeled data, a pronunciation distance predictor was trained and built for unlabeled data. Due to space limit in [1], the procedure for calculating the reference distances was not described in detail. Then in this paper, detailed descriptions are given and 498 world-wide native and non-native speakers in the Speech Accent Archive [2] are clustered using the phonetic reference distances. Results show high validity of using the calculated distances as reference distances for training a distance predictor.