Language model cross adaptation for LVCSR system combination

Computer Speech and Language

Volumn 27, Issue 4, 2013, Pages 928-942

  Liu, X ^a   Gales, M J F ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; CROSS SYSTEMS; ERROR RATE REDUCTION; LANGUAGE MODEL; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LINEAR COMBINATIONS; MODEL ADAPTATION; SYSTEM COMBINATION;

CONTINUOUS SPEECH RECOGNITION;

COMPUTATIONAL LINGUISTICS;

EID: 84875943582     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2012.07.010     Document Type: Article

References (55)

1. T. Alumäe, and M. Kurimo Domain adaptation of maximum entropy language models Proc. of the ACL 2010 Conference Short Papers 2010 Association for Computational Linguistics 301 306
2. T. Anastasakos, and S.V. Balakrishnan The use of confidence measures in unsupervised adaptation of speech recognizers Proc. ICSLP'98 Sydney 1998
3. Y. Bengio, and R. Ducharme A neural probabilistic language model Advances in Neural Information Processing Systems 3 2003 1137 1155
4. D. Blei, A. Ng, and M. Jordan Latent Dirichlet allocation Journal of Machine Learning Research 3 2003
5. I. Bulyko, M. Ostendorf, and A. Stolcke Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures Proc. HLT'03 Edmonton 2003
6. I. Bulyko, S. Matsoukas, R. Schwartz, L. Nguyen, and J. Makhoul Language model adaptation in machine translation from speech Proc. IEEE ICASSP2007 Hawaii 2007
7. L. Chen, J.-L. Gauvain, L. Lamel, G. Adda, and M. Adda Language model adaptation for broadcast news transcription Proc. ITRW'01 Paris 2001
8. J.T. Chien, M.S. Wu, and C.S. Wu Bayesian learning for latent semantic analysis Proc. ISCA Interspeech'05 Lisbon 2005
9. S.M. Chu The 2009 IBM GALE Mandarin broadcast transcription system Proc. IEEE ICASSP2010 Dallas 2010
10. J. Darroch, and D. Ratcliff Generalized iterative scaling for log-linear models The Annals of Mathematical Statistics 43 5 1972 1470 1480
11. A. Emami, and L. Mangu Empirical study of neural network language models of Arabic speech recognition Proc. IEEE ASRU2007 Kyoto 2007
12. G. Evermann, and P.C. Woodland Posterior probability decoding, confidence estimation and system combination Proc. Speech Transcription Workshop 2000
13. M. Federico Efficient language model adaptation through MDI estimation Proc. EuroSpeech'99 Budapest 1999
14. M. Federico Language model adaptation through topic decomposition and MDI estimation Proc. IEEE ICASSP2003 Hong Kong 2003
15. J.G. Fiscus A post-processing system to yield reduced word error rates: recogniser output voting error reduction (ROVER) Proc. IEEE ASRU1997 1997
16. M.J.F. Gales, and S.S. Airey Product of Gaussians for speech recognition Computer Speech and Language 20 January (1) 2006 22 40
17. M.J.F. Gales Speech system combination for machine translation Proc. IEEE ICASSP2007 Hawaii 2007
18. M.J.F. Gales Maximum likelihood linear transformations for HMM-based speech recognition Computer Speech and Language 12 2 1998 75 98
19. D. Gildea, and T. Hofmann Topic-based language models using EM Proc. Eurospeech'99 Budapest 1999
20. H. Hermansky Perceptual linear prediction (PLP) of speech Journal of the Acoustic Society of America 87 4 1990 1738 1752
21. J.L. Hieronymus, X. Liu, M.J.F. Gales, and P.C. Woodland Exploiting Chinese character models to improve speech recognition performance Proc. ISCA Interspeech'09 Brighton 2009
22. G. Hinton Products of experts Proc. ICANN 1999
23. G. Hinton Training products of experts by minimizing contrastive divergence Neural Computation 14 2002 1771 1800
24. B. Hsu Generalized linear interpolation of language models Proc. IEEE ASRU2007 Kyoto 2007
25. Kumar, N.; 1997. Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition. Ph.D. Thesis. John Hopkins University, Baltimore.
26. L. Lamel Improved models for Mandarin speech-to-text transcription Proc. IEEE ICASSP2011 Prague 2011
27. C.J. Leggetter, and P.C. Woodland Maximum likelihood linear regression for speaker adaptation of continuous density HMMs Computer Speech and Language 9 1995 171 186
28. X. Lei Development of the 2008 SRI Mandarin speech-to-text system for broadcast news and conversation Proc. ISCA Interspeech'09 Brighton 2009
29. X. Liu, M.J.F. Gales, and P.C. Woodland Automatic complexity control for HLDA systems Proc. IEEE ICASSP2003, vol. 1 Hong Kong 2003 132 135
30. X. Liu, M.J.F. Gales, and P.C. Woodland Context dependent language model adaptation Proc. ISCA Interspeech'08 Brisbane 2008
31. X. Liu, M.J.F. Gales, and P.C. Woodland Use of contexts in language model interpolation and adaptation Proc. ISCA Interspeech'09 Brighton 2009
32. X. Liu, M.J.F. Gales, J.L. Hieronymus, and P.C. Woodland Language model combination and adaptation using weighted finite state transducers Proc. IEEE ICASSP2010 Dallas 2010
33. X. Liu, M.J.F. Gales, and P.C. Woodland Language model cross adaptation for LVCSR system combination Proc. ISCA Interspeech'10 Makuhari 2010
34. X. Liu, M.J.F. Gales, J.L. Hieronymus, and P.C. Woodland Investigation of acoustic units for LVCSR systems Proc. IEEE ICASSP2011 Prague 2011
35. Liu, X.; Gales, M.J.F.; Woodland, P.C. Use of contexts in language model interpolation and adaptation. Computer Speech and Language, in press.
36. J. Luo, L. Lamel, and J.-L. Gauvain Modeling characters versus words for Mandarin speech recognition Proc. ICASSP2009 Taipei 2009
37. M. Mohri, and M. Riley Network optimizations for large vocabulary speech recognition Speech Communication 25 3 1998
38. D. Mrva, and P.C. Woodland A PLSA-based language model for conversational telephone speech Proc. ISCA Interspeech'04 Jeju 2004
39. T. Ng Progress in the BBN 2007 Mandarin speech to text system Proc. IEEE ICASSP2008 Las Vegas 2008
40. T. Ng Jointly optimized discriminative features for speech recognition Proc. ISCA Interspeech'10 Makuhari 2010
41. F.J. Och, and H. Ney Discriminative training and maximum entropy models for statistical machine translation Proc. ACL02' Philadelphia 2002 295 302
42. J. Park, X. Liu, M.J.F. Gales, and P.C. Woodland Improved neural network based language modelling and adaptation Proc. ISCA Interspeech'10 Makuhari 2010
43. B. Peskin Improvements in recognition of conversational telephone speech Proc. IEEE ICASSP1999 Phoenix 1999
44. D. Povey, and P.C. Woodland Minimum phone error and I-smoothing for improved discriminative training Proc. IEEE ICASSP2002 Orlando 2002
45. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah Boosted MMI for model and feature-space discriminative training Proc. IEEE ICASSP2008 Las Vegas 2008 4057 4060
46. R. Prasad The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system Proc. ISCA Interspeech'05 Lisboa 2005
47. R. Rosenfeld, S.F. Chen, and X. Zhu Whole-sentence exponential language models: a vehicle for linguistic-statistical integration Computers Speech and Language 15 1 2001
48. R. Schwartz Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system Proc. IEEE ICASSP2004 Montreal 2004
49. H. Schwenk Continuous space language models Computer Speech and Language 21 July (3) 2007 492 518
50. Y.C. Tam, and T. Schultz Dynamic language model adaptation using variational Bayes inference Proc. ISCA Interspeech'05 Lisboa 2005
51. M. Weintraub LM95 project report: fast training and portability 1995 Language Modeling Summer Research Workshop Technical Reports, Research Note 1 1996 Center for Language and Speech Processing, Johns Hopkins University Baltimore http://www-speech.sri.com/cgi-bin/run-distill?papers/lm95-report.ps.gz (accessed 26.03.12)
52. P.C. Woodland, C.J. Leggetter, J.J. Odell, V. Valtchev, and S.J. Young The 1994 HTK large vocabulary speech recognition system Proc. IEEE ICASSP1995 Detroit 1995
53. P.C. Woodland, M.J.F. Gales, D. Pye, and S.J. Young The development of the 1996 HTK broadcast news transcription system Proc. DARPA Speech Recognition Workshop Arden House, NY, US 1996 73 78
54. P.C. Woodland SuperEARS: multi-site broadcast news system Proc. Rich Transcription Workshop 2004 Palisades, NY 2004
55. F. Wallhoff, D. Willett, and G. Rigoll Frame discriminative and confidence-driven adaptation for LVCSR Proc. IEEE ICASSP2000 Istanbul 2000