Syllable language models for Mandarin speech recognition: Exploiting character language models

Journal of the Acoustical Society of America

Volumn 133, Issue 1, 2013, Pages 519-528

  Liu, Xunying ^a   Hieronymus, James L ^b   Gales, Mark J F ^a   Woodland, Philip C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUDIO-RECOGNITION; CHARACTER ERROR RATES; CHARACTER LEVEL; CHINESE LANGUAGE; LANGUAGE MODEL; LINGUISTIC INFORMATION; MANDARIN CHINESE; MANDARIN SPEECH RECOGNITION; MODEL-BASED OPC; SPEECH RECOGNITION PERFORMANCE; SPOKEN LANGUAGES; TEXT SOURCES; WORD LEVEL;

SPEECH RECOGNITION;

COMPUTATIONAL LINGUISTICS;

ARTICLE; AUTOMATED PATTERN RECOGNITION; AUTOMATIC SPEECH RECOGNITION; DECISION TREE; HUMAN; PHONETICS; SIGNAL PROCESSING; SPEECH; STATISTICAL MODEL;

DECISION TREES; HUMANS; LINEAR MODELS; PATTERN RECOGNITION, AUTOMATED; PHONETICS; SIGNAL PROCESSING, COMPUTER-ASSISTED; SPEECH ACOUSTICS; SPEECH RECOGNITION SOFTWARE;

EID: 84872073683     PISSN: 00014966     EISSN: None     Source Type: Journal    
DOI: 10.1121/1.4768800     Document Type: Article

References (44)

1. J. de Francis, The Chinese Language: Fact and Fantasy (University of Hawaii Press, Honolulu, 1984), pp. 1-344.
2. R. Sproat, C. Shih, N. Chang, and W. Gale, " A stochastic finite-state word-segmentation algorithm for Chinese.," Comput. Linguist. 22 (3), 377-404 (1996).
3. S. M. Chu, D. Povey, Hong-Kwang Kuo, L. Mangu, S. Zhang, Q. Shi, and Y. Qin, " The 2009 IBM GALE Mandarin broadcast transcription system.," in Proceedings of IEEE ICASSP2010, Dallas (2010).
4. M. J. F. Gales, X. Liu, R. Sinha, P. C. Woodland, K. Yu, S. Matsoukas, T. Ng, K. Nguyen, L. Nguyen, J.-L. Gauvain, L. Lamel, and A. Messaoudi, " Speech system combination for machine translation.," in Proceedings of IEEE ICASSP2007, Hawaii (2007).
5. T. Ng, B. Zhang, K. Nguyen, and L. Nguyen, " Progress in the BBN 2007 Mandarin speech to text system.," in Proceedings of IEEE ICASSP2008, Las Vegas (2008).
6. E. O. Selkirk, " The syllable.," in The Structure of Phonological Representations, edited by, H. van der Hulst, and, Norval Smieth, (Fortus, Dordrecht, 1982), Vol. 2, pp. 337-385.
7. H. Gu, C. Tseng, and L. Lee, " Markov modeling of Mandarin Chinese for decoding the phonetic sequence into Chinese characters.," Comput. Speech Lang. 5, 363-371 (1991). 10.1016/0885-2308(91)90004-A
8. J. L. Hieronymus, X. Liu, M. J. F. Gales, and P. C. Woodland, " Exploiting Chinese character models to improve speech recognition performance.," in Proceedings of Interspeech'09, Brighton (2009).
9. L. S. Lee, C. Y. Tseng, H. Y. Gu, F. H. Liu, C. H. Chang, Y. H. Lin, Y. Lee, S. L. Tu, S. H. Hsieh, and C. H. Chen, " Golden Mandarin (I)-A real-time Mandarin speech dictation machine for Chinese language with very large vocabulary.," IEEE Trans. Speech Audio Process. 1 (2), 158-179 (1993). 10.1109/89.222876
10. X. Liu, M. J. F. Gales, J. L. Hieronymus, and P. C. Woodland, " Language model combination and adaptation using weighted finite state transducers.," in Proceedings of IEEE ICASSP2010, Dallas (2010).
11. J. Luo, L. Lamel, and J-L. Gauvain, " Modeling characters versus words for Mandarin speech recognition.," in Proceedings of ICASSP2009 (2009).
12. H. M. Wang, T. H. Ho, R. C. Yang, J. L. Shen, B. R. Bai, J. C. Hong, W. P. Chen, T. L. Yu, and L. S. Lee, " Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary using limited training data.," IEEE Trans. Speech Audio Process. 5 (2), 195-200 (1997). 10.1109/89.554782
13. S. M. Katz, " Estimation of probabilities from sparse data for the language model component of a speech recognizer.," IEEE Trans. Acoust., Speech, Signal Process. 35 (3), 400-401 (1987). 10.1109/TASSP.1987.1165125
14. P. Clarkson and A. Robinson, " Language model adaptation using mixtures and an exponentially decaying cache.," in Proceedings of ICASSP1997, Munich (1997), pp. 799-802.
15. F. Jelinek and R. Mercer, " Interpolated estimation of Markov source parameters from sparse data.," in Pattern Recognition in Practice, edited by, E. S. Gelsema, and, L. N. Kanal, (Norh-Holland, Amsterdam, 1980), pp. 381-402.
16. R. Rosenfeld, " A maximum entropy approach to adaptive statistical language modeling.," Comput. Speech Lang. 10, 187-228 (1996). 10.1006/csla.1996.0011
17. I. Bulyko, M. Ostendorf, and A. Stolcke " Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures.," in Proceedings of HLT '03, Edmonton (2003).
18. L. Chen, J-L. Gauvain, L. Lamel, G. Adda, and M. Adda, " Language model adaptation for broadcast news trancription.," in Proceedings of ISCA ITRW '01, Paris (2001).
19. M. Federico, " Efficient language model adaptation through MDI estimation.," in Proceedings of EuroSpeech '99, Budapest (1999).
20. X. Liu, M. J. F. Gales, and P. C. Woodland, " Context dependent language model adaptation.," in Proceedings of Interspeech '08, Brisbane (2008).
21. X. Liu, M. J. F. Gales, and P. C. Woodland, " Use of contexts in language model interpolation and adaptation.," in Proceedings of Interspeech '09, Brighton (2009).
22. J. G. Fiscus, " A post-processing system to yield reduced word error rates: Recogniser output voting error reduction (ROVER).," in Proceedings of IEEE ASRU '97 (1997).
23. G. Evermann and P. C. Woodland, " Posterior probability decoding, confidence estimation and system combination.," in Proceedings of Speech Transcription Workshop 2000 (2000).
24. G. Hinton, " Training products of experts by minimizing contrastive divergence.," Neural Comput. 14, 1771-1800 (2002). 10.1162/ 089976602760128018
25. A. Stolcke, " SRILM-An extensible language modeling toolkit.," in Proceedings of ICSLP '02, Denver (2002).
26. S. J. Young, G. Evermann, M. J. F. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. C. Woodland, The HTK Book Version 3.4.1, http://htk.eng.cam.ac.uk/prot-docs/htk-book.shtml (2009) (last viewed 12/16/2011), pp. 1-374.
27. M. Mohri and M. Riley, " Network optimizations for large vocabulary speech recognition.," Speech Commun. 25 (3), 1-12 (1998). 10.1016/S0167-6393(98)00026-0
28. M. Mohri, F. C. N. Pereira, and M. Riley, " The design principles of a weighted finite-state transducer library.," Theor. Comput. Sci. 231, 17-32 (2000). 10.1016/S0304-3975(99)00014-6
29. M. Mohri, F. C. N. Pereira, and M. Riley, " Weighted finite-state transducers in speech recognition.," Comput. Speech Lang. 16 (1), 69-88 (2002). 10.1006/csla.2001.0184
30. M. Mohri, " Weighted automata algorithms.," in Handbook of Weighted Automata. Monographs in Theoretical Computer Science, edited by, Manfred Droste, Werner Kuich, and, Heiko Vogler, (Springer, Berlin, 2009), pp. 213-254.
31. J. Darroch and D. Ratcliff, " Generalized iterative scaling for log-linear models.," Ann. Math. Stat. 43 (5), 1470-1480 (1972). 10.1214/aoms/1177692379
32. R. Rosenfeld, S. F. Chen, and X. Zhu, " Whole-sentence exponential language models: A vehicle for linguistic-statistical integration.," Comput. Speech Lang. 15 (1), 55-73 (2001). 10.1006/csla.2000.0159
33. M. Weintraub, Y. Aksu, S. Dharanipragada, S. Khudanpur, H. Ney, J. Prange, A. Stolcke, F. Jelinek, and E. Shriberg, " LM95 project report: Fast training and portability.," in 1995 Language Modeling Summer Research Workshop Technical Reports, Research Note No. 1, Center for Language and Speech Processing, Johns Hopkins University, Baltimore (1996), http://www-speech.sri. com/cgi-bin/run-distill?papers/lm95-report.ps.gz (last viewed 12/16/2011).
34. P. C. Woodland, C. J. Leggetter, J. J. Odell, V. Valtchev, and S. J. Young, " The 1994 HTK large vocabulary speech recognition system.," in Proceedings of IEEE ICASSP1995, Detroit (1995).
35. D. A. Caseiro and I. Trancoso, " A specialized on-the-fly algorithm for lexicon and language model composition.," IEEE Trans. Audio, Speech, Lang. Process. 14 (4), 1281-1291 (2006). 10.1109/TSA.2005.860838
36. R. Sinha, M. J. F. Gales, D. Y. Kim, X. Liu, K. C. Kim, and P. C. Woodland, " The CU-HTK Mandarin broadcast news transcription system.," in Proceedings of IEEE ICASSP2006, Toulouse (2006).
37. D. Povey and P. C. Woodland, " Minimum phone error and I-smoothing for improved discriminative training.," in Proceedings of IEEE ICASSP2002, Orlando (2002).
38. S. J. Young, J. J. Odell, and P. C. Woodland, " Tree-based state tying for high accuracy acoustic modeling.," in Proceedings of ARPA Human Language Age Technology Workshop (Morgan Kaufman, Plainsboro, NJ, 1994), pp. 307-312.
39. C. J. Leggetter and P. C. Woodland, " Maximum likelihood linear regression for speaker adaptation of continuous density HMMs.," Comput. Speech Lang. 9, 171-186 (1995). 10.1006/csla.1995.0010
40. N. Kumar, " Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition.," Ph.D. thesis, John Hopkins University, Baltimore, 1997.
41. X. Liu, M. J. F. Gales, and P. C. Woodland, " Automatic complexity control for HLDA systems.," in Proceedings of IEEE ICASSP2003, Hong Kong (2003), Vol. 1, pp. 132-135.
42. P. C. Woodland, M. J. F. Gales, D. Pye, and S. J. Young, " The development of the 1996 HTK broadcast news transcription system.," in Proceedings of DARPA Speech Recognition Workshop (Arden House, New York, 1996), pp. 73-78.
43. S. F. Chen and J. T. Goodman, " An empirical study of smoothing techniques for language modeling.," Comput. Speech Lang. 13 (4), pp. 359-394 (1999). 10.1006/csla.1999.0128
44. H. Schwenk, " Continuous language models.," Comput. Speech Lang. 21 (3), 492-518 (2007). 10.1016/j.csl.2006.09.003