Characterizing Phonetic Transformations and Acoustic Differences Across English Dialects∗

Abstract — In this work, we propose a framework that au-tomatically discovers dialect-specific phonetic rules. These rules characterize when certain phonetic or acoustic transformations occur across dialects. To explicitly characterize these dialect-specific rules, we adapt the conventional hidden Markov model to handle insertion and deletion transformations. The proposed framework is able to convert pronunciation of one dialect to an-other using learned rules, recognize dialects using learned rules, retrieve dialect-specific regions, and refine linguistic rules. Poten-tial applications of our proposed framework include computer-assisted language learning, sociolinguistics, and diagnosis tools for phonological disorders. Index Terms—accent, phonological rules, informative dialect recognition, phonotactic modeling, pronunciation model I