Effective articulatory modeling for pronunciation error detection of L2 learner without non-native training data

Richeng Duan; Tatsuya Kawahara; Masatake Dantsuji; Jinsong Zhang

ICASSP 2017accepted0 citations

Effective articulatory modeling for pronunciation error detection of L2 learner without non-native training data

Richeng Duan, Tatsuya Kawahara, Masatake Dantsuji, Jinsong Zhang

Abstract

For effective articulatory feedback in computer-assisted pronunciation training (CAPT) systems, we address effective articulatory models of second language (L2) learners' speech without using such data, which is difficult to collect and annotate in a large scale. Context-dependent articulatory attributes (placement and manner of articulation) are modeled based on deep neural network (DNN). In order to efficiently train the non-native articulatory models, we exploit large speech corpora of native and target language to model inter-language phenomena. This multi-lingual learning is then combined with multi-task learning, which uses phone-classification as a sub-task. These methods are applied to Mandarin Chinese pronunciation learning by Japanese native speakers. Effects are confirmed in the native attribute classification and pronunciation error detection of non-native speech.

BibTeX

@inproceedings{icassp2017_effectivearticul,
  title = {Effective articulatory modeling for pronunciation error detection of L2 learner without non-native training data},
  author = {Richeng Duan and Tatsuya Kawahara and Masatake Dantsuji and Jinsong Zhang},
  booktitle = {ICASSP 2017},
  year = {2017}
}