Improvement of non-negative matrix factorization based language model using exponential models

2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings

Volumn , Issue , 2001, Pages 190-193

  Novak, M ^a   Mammone, R ^b  

^a IBM T J WATSON RESEARCH CENTER   (United States)

^b RUTGERS UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; FACTORIZATION; MATRIX ALGEBRA; SEMANTICS;

AUTOMATIC SPEECH RECOGNITION; EXPONENTIAL MODELS; LANGUAGE MODEL; LATENT SEMANTIC ANALYSIS; MODELING TECHNIQUE; NONNEGATIVE MATRIX FACTORIZATION; POSTERIORI; TOPIC LANGUAGES;

SPEECH RECOGNITION;

EID: 84962892214     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2001.1034619     Document Type: Conference Paper

References (9)

1. M. Novak and R. Mammone, "Use of non-negative matrix factorization for language model adaptation in a lecture transcription task," in Proceedings of ICASSP, Salt Lake City, Utah, May 2001.
2. J.R. Bellegarda, "A multispan language modelling framework for large vocabulary speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 6, no. 5, pp. 456-467, September 1998.
3. S. Della Pietra, V. Della Pietra, R.L. Mercer, and S. Roukos, "Adaptive language modeling using minimum discriminant estimation," Proceedings of the Speech and Natural Language DARPA Workshop, February 1992.
4. S.F. Chen, K. Seymore, and R. Rosenfeld, "Topic adaptation for language modeling using unnormalized exponential models," in Proceedings of ICASSP, Seattle, Washington, 1998.
5. S. Khudanpur and J. Wu, "A maximum entropy language model integrating n-grams and topic dependencies for conversational speech recognition," in Proceedings of ICASSP, Phoenix, Arizona, 1999.
6. R. Kuhn and R. De Mori, "A cache-based natural language model for speech reproduction," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 6, pp. 570-583, 1990.
7. D.D. Lee and H.S. Seung, "Learning the parts of objects by non-negative matrix factorization," Nature, vol. 401, pp. 1451-1454, October 1999.
8. J.N. Darroch and D. Ratcliff, "Generalized iterative scaling for log-linear models," Annals of Mathematical Statistics,, no. 43, pp. 1470-1480, 1972.
9. G. Faulkner, S. Gopal, A. Ittycheriah, R. Mammone, A. Medl, and M. Novak, "The aristotle project: A distributed learning system," in Proceedings of Ed-Media2000, World Conference on Educational Multimedia, Hypermedia, and Telecommunications, Montreal, Canada, June 2000, pp. 292-297.