E. Shriberg, L. Ferrer, S. Kajarekar, N. Scheffer, A. Stolcke and M. Akbacak, “Detecting nonnative speech using speaker recognition approaches,” in Proc. Odyssey 2008: The Speaker and Language Recognition Workshop, p. 26.
Detecting whether a talker is speaking his native language is useful for speaker recognition, speech recognition, and intelligence applications. We study the problem of detecting nonnative speakers of American English, using two standard speech corpora. We apply approaches effective in speaker verification to this task, including systems based on MLLR, phone N-gram, prosodic, and word N-gram features. Results show equal error rates between 12pct. and 20pct. depending on the system, test data, and choice of training data. Asymmetries in performance are most likely explained by differences in native language distributions in the corpora. Model combination yields substantial improvements over individual models, with the best result being around 8.6pct. EER.
While phone Ngrams are widely used in related tasks (e.g., language and dialect ID), we find that it is the least effective model in combination; MLLR, prosody, and word N-gram systems play stronger roles. Overall, results suggest that individual systems and system combinations found useful for speaker ID also offer promise for non-nativeness detection, and that further efforts are warranted in this area.