Using out-of-domain data to improve in-domain language models

IEEE Signal Processing Letters

Volumn 4, Issue 8, 1997, Pages 221-223

  Lyer, Rukmini ^a   Ostendorf, Mari ^a   Gish, Herb ^b  

^a Boston University   (United States)

^b Bolt Beranek/Newman Syst/T   (United States)

Author keywords

Lanugage modeling; Out of domain training

Indexed keywords

COMPUTATIONAL LINGUISTICS; ERROR CORRECTION; INTERPOLATION; MATHEMATICAL MODELS; SIGNAL THEORY;

LANGUAGE MODELS;

SPEECH RECOGNITION;

EID: 0031209168     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/97.611282     Document Type: Article

References (9)

1. P. Brown el al., "Class-based n-gram language models of natural language," Computat. Linguist., vol. 18, pp. 467-179, 1992.
2. R. Rohlicek, Y. Chow, and S. Roucos, "Statistical language modeling using a small corpus from an application domain," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, New York, NY, 1988, vol. 1. pp. 267-270.
3. S. Besling and H.-G. Meier, "Language model speaker adaptation." in Proc. Europ. Conf. Speech Communications and Technology. Sept. 1995, vol. 3. pp. 1755-1759.
4. T. Niesler and P. Woodland, "Combination of word-based and category-based language models," in Proc. Int. Conf. Spoken Language Processing, Oct. 1996, vol. 1, pp. 220-223.
5. P. Placeway, R. Schwanz, P. Fung, and L. Nguyen, "Estimation of powerful LM from small and large corpora," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, Apr. 1993, vol. 2, pp. 33-36.
6. R. lyer, "Language modeling with sentence-level mixtures," Masters thesis, Boston Univ., Boston, MA (anonymous ftp to raven.bu.edu. pub/reports directory), 1994.
7. J. J. Godfrey, E. C. Holliman, and J. McDaniel, "Switchboard: Telephone speech corpus for research and development," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing. Mar. 1992, vol. 1, pp. 517-520.
8. M. Ostendorf et al., "Integration of diverse recognition methodologies through reevaluation of n-best sentence hypotheses," in Proc. ARPA Workshop Speech and Nalurat Language, Feb. 1991, pp. 83-87.
9. L. Nguyen et al., "The 1994 BBN/BYBLOS speech recognition system," in Proc. ARPA Workshop Spoken Language Technology. Mar. 1994, pp. 77-81.