INTERSPEECH 2010
11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Landmark-Based Automated Pronunciation Error Detection

Su-Youn Yoon (1), Mark Hasegawa-Johnson (2), Richard Sproat (3)

(1) Educational Testing Service, USA
(2) University of Illinois at Urbana-Champaign, USA
(3) Oregon Health & Science University, USA

We present a pronunciation error detection method for second language learners of English (L2 learners). The method is a combination of confidence scoring at the phone level and landmark-based Support Vector Machines (SVMs). Landmark-based SVMs were implemented to focus the method on targeting specific phonemes in which L2 learners make frequent errors. The method was trained on the phonemes that are difficult for Korean learners and tested on intermediate Korean learners. In the data where non-phonemic errors occurred in a high proportion, the SVM method achieved a significantly higher F-score (0.67) than confidence scoring (0.60). However, the combination of the two methods without the appropriate training data did not lead to improvement. Even for intermediate learners, a high proportion of errors (40%) was related to these difficult phonemes. Therefore, a method that is specialized for these phonemes would be beneficial for both beginners and intermediate learners.

Full Paper

Bibliographic reference.  Yoon, Su-Youn / Hasegawa-Johnson, Mark / Sproat, Richard (2010): "Landmark-based automated pronunciation error detection", In INTERSPEECH-2010, 614-617.