2020年
Cross-Lingual Transfer Learning of Non-Native Acoustic Modeling for Pronunciation Error Detection and Diagnosis.
IEEE ACM Trans. Audio Speech Lang. Process.
- ,
- ,
- ,
- 巻
- 28
- 号
- 開始ページ
- 391
- 終了ページ
- 401
- 記述言語
- 掲載種別
- 研究論文(学術雑誌)
- DOI
- 10.1109/TASLP.2019.2955858
© 2014 IEEE. In computer-assisted pronunciation training (CAPT), the scarcity of large-scale non-native corpora and human expert annotations are two fundamental challenges to non-native acoustic modeling. Most existing approaches of acoustic modeling in CAPT are based on non-native corpora while there are so many living languages in the world. It is impractical to collect and annotate every non-native speech corpus considering different language pairs. In this work, we address non-native acoustic modeling (both on phonetic and articulatory level) based on transfer learning. In order to effectively train acoustic models of non-native speech without using such data, we propose to exploit two large native speech corpora of learner's native language (L1) and target language (L2) to model cross-lingual phenomena. This kind of transfer learning can provide a better feature representation of non-native speech. Experimental evaluations are carried out for Japanese speakers learning English. We first demonstrate the proposed acoustic-phone model achieves a lower word error rate in non-native speech recognition. It also improves the pronunciation error detection based on goodness of pronunciation (GOP) score. For diagnosis of pronunciation errors, the proposed acoustic-articulatory modeling method is effective for providing detailed feedback at the articulation level.
- リンク情報
-
- DOI
- https://doi.org/10.1109/TASLP.2019.2955858
- DBLP
- https://dblp.uni-trier.de/rec/journals/taslp/DuanKDN20
- URL
- https://dblp.uni-trier.de/db/journals/taslp/taslp28.html#DuanKDN20
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85075655384&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85075655384&origin=inward
- ID情報
-
- DOI : 10.1109/TASLP.2019.2955858
- ISSN : 2329-9290
- eISSN : 2329-9304
- DBLP ID : journals/taslp/DuanKDN20
- SCOPUS ID : 85075655384