Cross-Lingual Phone Mapping for Large Vocabulary Speech Recognition of Under-Resourced Languages
-
- DO Van Hai
- School of Computer Engineering, Nanyang Technological University Temasek Laboratories@NTU, Nanyang Technological University
-
- XIAO Xiong
- Temasek Laboratories@NTU, Nanyang Technological University
-
- CHNG Eng Siong
- School of Computer Engineering, Nanyang Technological University Temasek Laboratories@NTU, Nanyang Technological University
-
- LI Haizhou
- School of Computer Engineering, Nanyang Technological University Temasek Laboratories@NTU, Nanyang Technological University Institute for Infocomm Research
抄録
This paper presents a novel acoustic modeling technique of large vocabulary automatic speech recognition for under-resourced languages by leveraging well-trained acoustic models of other languages (called source languages). The idea is to use source language acoustic model to score the acoustic features of the target language, and then map these scores to the posteriors of the target phones using a classifier. The target phone posteriors are then used for decoding in the usual way of hybrid acoustic modeling. The motivation of such a strategy is that human languages usually share similar phone sets and hence it may be easier to predict the target phone posteriors from the scores generated by source language acoustic models than to train from scratch an under-resourced language acoustic model. The proposed method is evaluated using on the Aurora-4 task with less than 1 hour of training data. Two types of source language acoustic models are considered, i.e. hybrid HMM/MLP and conventional HMM/GMM models. In addition, we also use triphone tied states in the mapping. Our experimental results show that by leveraging well trained Malay and Hungarian acoustic models, we achieved 9.0% word error rate (WER) given 55 minutes of English training data. This is close to the WER of 7.9% obtained by using the full 15 hours of training data and much better than the WER of 14.4% obtained by conventional acoustic modeling techniques with the same 55 minutes of training data.
収録刊行物
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E97.D (2), 285-295, 2014
一般社団法人 電子情報通信学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390282679356105728
-
- NII論文ID
- 130003394831
-
- ISSN
- 17451361
- 09168532
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可