CLASS-COMBINED ORD N-GRAM FOR ROBUST LANGUAGE ODELING

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 1599-1602

  Kobayashi, Norihiko ^a   Kobayashi, Tetsunori ^a  

^a WASEDA UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; SPEECH RECOGNITION;

A-WEIGHTING; BIGRAMS; LANGUAGE MODEL; N-GRAMS; PERFORMANCE; RECOGNITION ACCURACY; SPEECH CORPORA; TEXT CORPORA; WEIGHTING FUNCTIONS; WORD FREQUENCIES;

SPEECH COMMUNICATION;

EID: 18644377095     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. P.F.Brown et al., "Class-based N-gram Models of Natural Language," Computational Linguistics, Vol18, No.4, pp.467-479, 1992.
2. W.Ward, S.Issar, "A Class Based Language Model for Speech Recognition," IEEE Proc. ICASSP96, pp.416-418, 1996.
3. F.Jelinek, R.L.Mercer, "Interpolated Estimation of Markov Source Parameters from Sparse Data, In Pattern Recognition in Practice, pp.381397. North Holand, 1980.
4. H.Masataki, Y.Sagisaka, "Variable-order TV-gram generation by Word-class splitting and Consecutive Word Grouping," Proc. ICASSP96, pp.188-191, Mar. 1996.
5. T.R.Niesler, P.C.Woodland, "Combination of Word-Based and Category-Based Language Models,' Proc.ICSLP96, pp.1779-1782, 1997.
6. 7. Reichl, "A Class-based Language Model for Large-vocabulary Speech Recognition extracted from Part-of-speech Statistics," IEEE Proc. ICASSP'99, pp.537-540, May 1999.
7. Y. Hidaki, T. Kobayashi, "Combination of Word bigram and Class bigram for Topic-robust Language Modeling," IPSJ SIG-SLP Note, Vol98, No.12, pp.25-32, Feb.1998. (In Japanese)
8. M. Jardino, G. Adda, "Automatic Word Clas sification Using Simulated Annealing," IEEE Proc.ICASSP93, pp.4144, 1993.
9. Itou et al., "JNAS: Japanese Speech Corpus for Large Vocabulary Continuous Speech Recogni tion Research," Journal of the Acoustic Society Japan (E), Vol20, No.3, pp.199-206, May 1999.