Non-native English speech recognition using bilingual English lexicon and acoustic models

@inproceedings{citeulike:1854152, abstract = {This paper proposes an English speech recognition system which can recognize both non-native (i.e. Japanese) and native English speakers' pronunciation of English speech. The system uses a bilingual pronunciation lexicon in which each word has both English and Japanese phoneme transcriptions. The Japanese transcription is constructed considering typical Japanese pronunciation of English. Japanese and English acoustic models are used in recognizing both transcriptions, and the highest-likelihood word sequence obtained in combining with native English- and Japanese-pronounced words is the recognition result. Continuous speech recognition experiments show that the proposed system greatly improves Japanese-English speech recognition performance while maintaining the same performance level as that of a purely native English recognition system.}, author = {Matsunaga, S. and Ogawa, A. and Yamaguchi, Y. and Imamura, A. }, booktitle = {Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on}, citeulike-article-id = {1854152}, journal = {Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on}, keywords = {asr, hccl, nonnative}, pages = {I-340--I-343 vol.1}, posted-at = {2007-11-02 03:17:54}, priority = {2}, title = {Non-native English speech recognition using bilingual English lexicon and acoustic models}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1198787}, volume = {1}, year = {2003} }

TY - CONF ID - citeulike:1854152 L3 - citeulike-article-id:1854152 TI - Non-native English speech recognition using bilingual English lexicon and acoustic models T2 - Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on JF - Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on VL - 1 SP - I-340 EP - I-343 vol.1 N2 - This paper proposes an English speech recognition system which can recognize both non-native (i.e. Japanese) and native English speakers' pronunciation of English speech. The system uses a bilingual pronunciation lexicon in which each word has both English and Japanese phoneme transcriptions. The Japanese transcription is constructed considering typical Japanese pronunciation of English. Japanese and English acoustic models are used in recognizing both transcriptions, and the highest-likelihood word sequence obtained in combining with native English- and Japanese-pronounced words is the recognition result. Continuous speech recognition experiments show that the proposed system greatly improves Japanese-English speech recognition performance while maintaining the same performance level as that of a purely native English recognition system. KW - asr KW - hccl KW - nonnative AU - Matsunaga, S AU - Ogawa, A AU - Yamaguchi, Y AU - Imamura, A PY - 2003/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1198787 ER -