Use of contexts in language model interpolation and adaptation

Computer Speech and Language

Volumn 27, Issue 1, 2013, Pages 301-321

  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

CHARACTER ERROR RATES; COMPONENT MODEL; CONTEXT DEPENDENT; CONTEXT INDEPENDENT; CORPUS SIZE; DECODING ALGORITHM; DISCRIMINATIVE APPROACH; DISCRIMINATIVE TRAINING; INDIVIDUAL COMPONENTS; LANGUAGE MODEL; MANDARIN CHINESE; MAP ADAPTATION; MAP ESTIMATION; ROBUST ESTIMATION; ROBUST WEIGHT; SPEECH TRANSCRIPTIONS; TEST DATA; TRAINING DATA; WEIGHT INFORMATION; WEIGHTED FINITE-STATE TRANSDUCERS; WEIGHTING FUNCTIONS; WORD CONTEXTS;

COMPUTATIONAL LINGUISTICS; ESTIMATION; SPEECH TRANSMISSION;

INTERPOLATION;

EID: 84867332205     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2012.06.004     Document Type: Article

References (59)

1. L. Bahl The IBM large vocabulary continuous speech recognition system for the ARPA NAB news task Proceedings of the ARPA Workshop on Spoken Language Technology 1995 121 126
2. J. Bellegarda Exploiting latent semantic information in statistical language modeling Proceedings of the IEEE 88 August (8) 2000 1279 1296
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. T. Brants Test data likelihood for PLSA models Information Retrieval 8 2 2005 181 196
6. I. Bulyko, M. Ostendorf, and A. Stolcke Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures Proceedings of the HLT'03 Edmonton 2012
7. I. Bulyko, S. Matsoukas, R. Schwartz, L. Nguyen, and J. Makhoul Language model adaptation in machine translation from speech Proceedings of the ICASSP'07 Hawaii 2007
8. D.A. Caseiro, and I. Trancoso A specialized on-the-fly algorithm for lexicon and language model composition IEEE Transactions on Audio, Speech, and Language Processing 14 4 2006 1281 1291
9. S.F. Chen, and J.T. Goodman An empirical study of smoothing techniques for language modeling Computer Speech and Language 13 4 1999 359 394
10. L. Chen, J.-L. Gauvain, L. Lamel, G. Adda, and M. Adda Language model adaptation for broadcast news transcription Proceedings of the ISCA ITRW'01 Paris 2001
11. O. Cheng, J. Dines, and M.M. Doss A generalized dynamic composition algorithm of weighted finite state transducers for large vocabulary speech recognition Proceedings of the ICASSP'07 Hawaii 2007
12. J.T. Chien, M.S. Wu, and C.S. Wu Bayesian learning for latent semantic analysis Proceedings of the Interspeech'05 Lisbon 2005
13. P. Clarkson, and A. Robinson Language model adaptation using mixtures and an exponentially decaying cache Proceedings of the ICASSP1997 Munich 1997 799 802
14. J. Darroch, and D. Ratcliff Generalized iterative scaling for log-linear models The Annals of Mathematical Statistics 43 5 1972 1470 1480
15. V. Doumpiotis, and W. Byrne Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition Speech Communication 2 2005 142 160
16. M. Federico Efficient language model adaptation through MDI estimation Proceedings of the EuroSpeech'99 Budapest 1999
17. M. Federico Language model adaptation through topic decomposition and MDI estimation Proceedings of the IEEE ICASSP2003 Hong Kong 2003
18. D. Gildea, and T. Hofmann Topic-based language models using EM Proceedings of the Eurospeech'99 Budapest 1999
19. P.S. Gopalakrishnan, D. Kanevsky, A. Nádas, and D. Nahamoo An inequality for rational functions with applications to some statistical estimation problems IEEE Transactions on Information Theory 37 January (1) 1991
20. H. Hermansky Perceptual linear prediction (PLP) of speech Journal of the Acoustic Society of America 87 4 1990 1738 1752
21. G. Hinton Training products of experts by minimizing contrastive divergence Neural Computation 14 2002 1771 1800
22. J.L. Hieronymus, X. Liu, M.J.F. Gales, and P.C. Woodland Exploiting Chinese character models to improve speech recognition performance Proceedings of the Interspeech'09 Brighton 2009
23. B. Hsu Generalized linear interpolation of language models Proceedings of the IEEE ASRU'07 Kyoto 2007
24. R. Iyer, M. Ostendorf, and R. Rohlicek An improved language model using a mixture of Markov components Proceedings of the ARPA Workshop on Human Language Technology Plainsboro, NJ 1994 82 87
25. R. Iyer, and M. Ostendorf Modeling long distance dependence in language: topic mixtures vs. dynamic cache models IEEE Transactions on Speech and Audio Processing 7 January (1) 1999 30 39
26. F. Jelinek, and R. Mercer Interpolated estimation of Markov source parameters from sparse data E.S. Gelsema, L.N. Kanal, Pattern Recognition in Practice 1980 North Holland Amsterdam 381 402
27. F. Jelinek Statistical Methods for Speech Recognition 1997 MIT Press Cambridge, Massachusetts
28. S.M. Katz Estimation of probabilities from sparse data for the language model component of a speech recognizer IEEE Transactions on Acoustics, Speech, and Signal Processing 35 3 1987 400 401
29. J. Kaiser, B. Horvat, and Z. Kacic A novel loss function for the overall risk-criterion based discriminative training of HMM models Proceedings of the ICSLP'00 Beijing 2012
30. R. Kneser, and V. Steinbiss On the dynamic adaptation of stochastic LM Proceedings of the ICASSP1993, vol. 2 Minneapolis 1993 586 589
31. R. Kneser, and J. Peters Semantic clustering for adaptive language modeling Proceedings of the ICASSP1997, vol. 2 Munich 1997 779 782
32. Kumar, N.; 1997. Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition. PhD Thesis. John Hopkins University, Baltimore.
33. X. Liu, M.J.F. Gales, and P.C. Woodland Automatic complexity control for HLDA systems Proceedings of the IEEE ICASSP2003, vol. 1 Hong Kong 2003 132 135
34. X. Liu, W.J. Byrne, M.J.F. Gales, and P.C. Woodland Discriminative language model adaptation for Mandarin broadcast speech transcription and translation Proceedings of the IEEE ASRU'07 Kyoto 2007
35. X. Liu, M.J.F. Gales, and P.C. Woodland Context dependent language model adaptation Proceedings of the Interspeech'08 Brisbane 2008
36. X. Liu, M.J.F. Gales, and P.C. Woodland Use of contexts in language model interpolation and adaptation Proceedings of the Interspeech'09 Brighton 2009
37. X. Liu, M.J.F. Gales, J.L. Hieronymus, and P.C. Woodland Language model combination and adaptation using weighted finite state transducers Proceedings of the IEEE ICASSP2010 Dallas 2010
38. J. McDonough, E. Stoimenov, and D. Klakow An algorithm for fast composition of weighted finite-state transducers Proceedings of the ASRU'07 Kyoto 2007
39. D. Mrva, and P.C. Woodland A PLSA-based language model for conversational telephone speech Proceedings of the InterSpeech'04 Jeju 2004
40. D. Mrva, and P.C. Woodland Unsupervised language model adaptation for Mandarin broadcast conversation transcription Proceedings of the ICSLP'06 Pittsburgh 2006
41. M. Mohri Finite-state transducers in language and speech processing Computational Linguistics 23 2 1997 269 311
42. M. Mohri, and M. Riley Network optimizations for large vocabulary speech recognition Speech Communication 25 3 1998
43. M. Mohri, M. Riley, D. Hindle, A. Ljolje, and F. Pereira Full expansion of context-dependent networks in large vocabulary speech recognition Proceedings of the ICASSP'98 Seattle 1998
44. M. Mohri, F. Pereira, and M. Riley Weighted finite-state transducers in speech recognition Proceedings of the ASR2000 Paris 2000
45. Normandin, Y.; 1991. Hidden Markov models maximum mutual information estimation and the speech recognition problem. PhD Thesis. McGill University, Canada.
46. F.J. Och, and H. Ney Discriminative training and maximum entropy models for statistical machine translation Proceedings of the ACL02' Philadelphia 2012 295 302
47. T. Oonishi, P. Dixon, K. Iwano, and S. Furui Generalization of specialized on-the-fly composition Proceedings of the ICASSP'09 Taipei 2009
48. S. Della Pietra, V. Della Pietra, R.L. Mercer, and S. Roukos Adaptive language modeling using minimum discriminant estimation Proceedings of the ICASSP'92 San Francisco 1992 1633 1636
49. D. Povey, and P.C. Woodland Minimum phone error and I-smoothing for improved discriminative training Proceedings of the ICASSP'02 Orlando 2002
50. R. Rosenfeld A maximum entropy approach to adaptive statistical language modeling Computer Speech and Language 10 1996 187 228
51. R. Rosenfeld Two decades of statistical language modeling: where do we go from here? Proceedings of the IEEE 88 August (8) 2000
52. 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 2001
53. H. Schwenk Continuous space language models Computer Speech and Language 21 July (3) 2007 492 518
54. K. Seymore, and R. Rosenfeld Using story topics for language model adaptation Proceedings of the Eurospeech'97 Rhodes 1997
55. A. Stolcke SRILM - an extensible language modeling toolkit Proceedings of the Proceedings of the ICSLP'02 Denver 2002
56. R. Sinha, M.J.F. Gales, D.Y. Kim, X. Liu, K.C. Sim, and P.C. Woodland The CU-HTK Mandarin broadcast news transcription system Proceedings of the ICASSP'06 Toulouse 2006
57. Y.C. Tam, and T. Schultz Dynamic language model adaptation using variational Bayes inference Proceedings of the Interspeech'05 Lisbon 2005
58. P.C. Woodland, M.J.F. Gales, D. Pye, and S.J. Young The development of the 1996 HTK broadcast news transcription system Proceedings of the DARPA Speech Recognition Workshop Arden House, NY, USA 1996 73 78
59. Young, S.; et al.; 2009. The HTK Book Version 3.4.1.