Comparing classifiers for pronunciation error detection

Providing feedback on pronunciation errors in computer assisted language learning systems requires that pronunciation errors be detected automatically. In the present study we compare four types of classifiers that can be used for this purpose: two acoustic-phonetic classifiers (one of which employs linear-discriminant analysis (LDA)), a classifier based on cepstral coefficients in combination with LDA, and one based on confidence measures (the so-called Goodness Of Pronunciation scores). The best results were obtained for the two LDA classifiers which produced accuracy levels of about 85-93%.

[1]  Helmer Strik,et al.  Segmental errors in Dutch as a second language: How to establish priorities for CAPT , 2004 .

[2]  J D Miller,et al.  Plosive/fricative distinction: the voiceless case. , 1990, The Journal of the Acoustical Society of America.

[3]  Silke M. Witt,et al.  Use of speech recognition in computer-assisted language learning , 2000 .

[4]  Helmer Strik,et al.  ASR corrective feedback on pronunciation: Does it really work? , 2006 .

[5]  Helmer Strik,et al.  Selecting segmental errors in non-native Dutch for optimal pronunciation training , 2006 .

[6]  Akinori Ito,et al.  Pronunciation error detection method based on error rule clustering using a decision tree , 2005, INTERSPEECH.

[7]  Jean-Pierre Martens,et al.  On The Use of Phonological Features for Pronunciation Scoring , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[8]  Yoon Kim,et al.  Automatic pronunciation scoring of specific phone segments for language instruction , 1997, EUROSPEECH.

[9]  Tatsuya Kawahara,et al.  Recognition and verification of English by Japanese students for computer-assisted language learning system , 2002, INTERSPEECH.

[10]  L. Boves,et al.  Quantitative assessment of second language learners' fluency by means of automatic speech recognition technology. , 2000, The Journal of the Acoustical Society of America.

[11]  Steve J. Young,et al.  Phone-level pronunciation scoring and assessment for interactive language learning , 2000, Speech Commun..

[12]  Lou Boves,et al.  Creation and analysis of the dutch polyphone corpus , 1994, ICSLP.

[13]  Helmer Strik,et al.  Automatic detection of frequent pronunciation errors made by L2-learners , 2005, INTERSPEECH.

[14]  Khiet P. Truong,et al.  Automatic pronunciation error detection in Dutch as a second language: an acoustic-phonetic approach , 2004 .

[15]  Paul Boersma,et al.  Praat, a system for doing phonetics by computer , 2002 .

[16]  Yik-Cheung Tam,et al.  PLASER: Pronunciation Learning via Automatic Speech Recognition , 2003, HLT-NAACL 2003.