Automatic Pronunciation Transliteration for Chinese-English Mixed Language Keyword Spotting

This paper presents automatic pronunciation transliteration method with acoustic and contextual analysis for Chinese-English mixed language keyword spotting (KWS) system. More often, we need to develop robust Chinese-English mixed language spoken language technology without Chinese accented English acoustic data. In this paper, we exploit pronunciation conversion method based on syllable-based characteristic analysis of pronunciation and data-driven phoneme pairs mappings to solve mixed language problem by only using well-trained Chinese models. One obvious advantage of such method is that it provides a flexible framework to implement the pronunciation conversion of English keywords to Chinese automatically. The efficiency of the proposed method was demonstrated under KWS task on mixed language database.

[1]  Peng Liu,et al.  Cross-lingual speech recognition under runtime resource constraints , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Haizhou Li,et al.  A phonetic similarity model for automatic extraction of transliteration pairs , 2007, TALIP.

[3]  Hynek Hermansky,et al.  Exploiting phoneme similarities in hybrid HMM-ANN keyword spotting , 2007, INTERSPEECH.

[4]  Jia-Jang Tu,et al.  Chinese-English mixed-lingual keyword spotting , 2004, 2004 International Symposium on Chinese Spoken Language Processing.

[5]  Elizabeth C. Botha,et al.  An acoustic distance measure for automatic cross-language phoneme mapping , 2001 .

[6]  Gunnar Evermann,et al.  Large vocabulary decoding and confidence estimation using word posterior probabilities , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[7]  Shrikanth S. Narayanan,et al.  Language-adaptive persian speech recognition , 2003, INTERSPEECH.

[8]  Le Sun,et al.  A Syllable-based Name Transliteration System , 2009, NEWS@IJCNLP.