Variable n-grams and extensions for conversational speech language modeling

IEEE Transactions on Speech and Audio Processing

Volumn 8, Issue 1, 2000, Pages 63-75

  Siu, Manhung ^a,b   Ostendorf, Mari ^a,c  

^a IEEE   (Hong Kong)

^b HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

^c UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; MATHEMATICAL MODELS; SPEECH RECOGNITION;

CONVERSATIONAL SPEECH LANGUAGE MODELING;

SPEECH SYNTHESIS;

EID: 0033873049     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.817454     Document Type: Article

References (32)

1. K. L. A. Waibel Self organized language modeling for speech recognition Readings in Speech Recognition 450 506 1991 Morgan Kaufman CA, San Mateo
2. L. Bahl P. Brown P. deSouza R. Mercer A tree-based statistical language model for natural language speech recognition IEEE Trans. Acoust., Speech, Signal Processing 37 1001 1008 1989 29 1399 32278
3. L. N. K. E. S. Gelsema Estimation of Markov source parameters from sparse data Pattern Recognition in Practice 381 397 1980 North-Holland The Netherlands, Amsterdam
4. I. H. Witten T. C. Bell The zero-frequency problem: Estimation the probabilities of novel events in adaptive text compression IEEE Trans. Inform. Theory 37 1085 1094 1991 18 2832 87000
5. S. M. Katz Estimation of probabilities from sparse data for the language model component of a speech recognizer IEEE Trans. Acoust., Speech, Signal Processing ASSP-35 400 401 1987
6. P. Placeway R. Schwartz P. Fung L. Nguyen The estimation of powerful language models from small and large corpora Proc. Int. Conf. Acoustics, Speech, and Signal Proc. 33 36 1993 1051 7685 319222
7. S. Chen J. Goodman An empirical study of smoothing techniques for language modeling Comput. Speech Lang. 13 359 393 1999
8. J. Billa Multilingual speech recognition: The 1996 BYBLOS Callhome system Proc. Eur. Conf. Speech Communication and Technology 363 366 Proc. Eur. Conf. Speech Communication and Technology 1997
9. S. Wegmann Speaker normalization on conversational telephone speech Int. Conf. Acoustics, Speech, and Signal Processing 339 341 1996 3856 11264 541101
10. P. Brown Class-based n-gram models of natural language Comput. Linguist. 18 467 479 1992
11. R. Kneser H. Ney Improved clustering techniques for class-based statistical language modeling Proc. Eur. Conf. Speech Communication and Technology 973 976 Proc. Eur. Conf. Speech Communication and Technology 1993
12. T. Niesler P. Woodland Variable-length category n-gram language models Comput. Speech Lang. 21 1 26 1999
13. I. Iyer M. Ostendorf Transforming out-of-domain estimates to improve in-domain language models Proc. Eur. Conf. Speech Communication and Technology 1975 1978 1997
14. E. E. Shriberg Preliminaries to a theory of speech disfluencies 1994 Ph.D. dissertation Berkeley
15. A. Stolcke E. Shriberg Statistical language modeling for speech disfluency Proc. Int. Conf. Acoustics, Speech, Signal Processing 405 408 Proc. Int. Conf. Acoustics, Speech, Signal Processing 1996 3856 11264 541118
16. E. Shriberg A. Stolcke Word predictability after hesitations: A corpus-based study Proc. Conf. Spoken Language Processing 1868 1871 Proc. Conf. Spoken Language Processing 1996 4822 13325 607996
17. M Siu M. Ostendorf H. Gish Modeling disfluencies in conversational speech Proc. Int. Conf. Spoken Language Processing 1 386 389 1996 4822 13323 607135
18. J. Cowan G. Tesauro J. Alspector The power of amnesia Advances in Neural Information Processing Systems 6 176 183 1994 Morgan Kaufmann CA, San Mateo
19. I. Guyon F. Pereira Design of a linguistic postprocessor using variable memory length Markov models Proc. 3rd ICDAR 454 457 Proc. 3rd ICDAR 1995 4755 13183 599034
20. R. Kneser Statistical language modeling using a variable context length Proc. Int. Conf. Spoken Language Processing 494 497 Proc. Int. Conf. Spoken Language Processing 1996 4822 13323 607162
21. K. Seymore R. Rosenfeld Scalable backoff language models Proc. Int. Conf. Spoken Language Processing 232 235 Proc. Int. Conf. Spoken Language Processing 1996 4822 13323 607084
22. A. Stolcke Entropy-based pruning of backoff language models Proc. DARPA Broadcast News Transcription and Understanding Workshop 270 274 Proc. DARPA Broadcast News Transcription and Understanding Workshop 1998
23. G. Riccardi E. Bocchieri R. Pieraccini Nondeterministic stochastic language models for speech recognition Proc. Int. Conf. Acoust., Speech, Signal Processing 237 240 1995 3469 10215 479408
24. M. Siu Learning local lexical structure of conversational speech 1998 Ph.D. dissertation MA, Boston
25. J. Rissanen Stochastic complexity J. R. Stat. Soc. B 49 223 239 1987
26. A. Nadas On Turing's formula for word probabilities IEEE Trans. Acoust., Speech, Signal Processing ASSP-33 1414 1416 Dec. 1985
27. J. J. Godfrey E. C. Holliman J. McDaniel SWITCHBOARD: Telephone speech corpus for research and development Proc. Int. Conf. Acoustics, Speech, and Signal Processing 517 520 Proc. Int. Conf. Acoustics, Speech, and Signal Processing 1992 626 5894 225858
28. A. Stolcke E. Shriberg Automatic linguistic segmentation of conversational speech Proc. Int. Conf. Spoken Language Processing 1005 1007 Proc. Int. Conf. Spoken Language Processing 1996 4822 13324 607773
29. E. S. Ristad R. G. Thomas Nonuniform Markov models Proc. Int. Conf. Acoust., Speech, Signal Processing 791 794 Proc. Int. Conf. Acoust., Speech, Signal Processing 1997 4635 13030 596046
30. F. Jelinek Statistical Methods for Speech Recognition 1998 MIT Press MA, Cambridge
31. H. Ney U. Essen R. Kneser On structuring probabilistic dependences in stochastic language modeling Comput. Speech Lang. 8 1 38 1994
32. M. Meteer R. Iyer Modeling conversational speech for speech recognition Proc. Conf. Empirical Methods in Natural Language Processing Proc. Conf. Empirical Methods in Natural Language Processing 1996