Compact n-gram models by incremental growing and clustering of histories

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2, Issue , 2006, Pages 1037-1040

  Virpioja, Sami ^a   Kurimo, Mikko ^a  

^a AALTO UNIVERSITY   (Finland)

Author keywords

Clustering; Information radius; Language models; Speech recognition

Indexed keywords

COMPUTATIONAL LINGUISTICS; DEEP NEURAL NETWORKS;

CLUSTERING; INFORMATION RADIUS; LANGUAGE MODEL; LARGE VOCABULARY SPEECH RECOGNITION; MAXIMUM A POSTERIORI ESTIMATION; N-GRAM LANGUAGE MODELS; RESTRICTED MODELS; TARGET LANGUAGE;

SPEECH RECOGNITION;

EID: 44949140825     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. A. Stolcke, "Entropy-based pruning of backoff language models," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, 1998, pp. 270-274.
2. V. Siivola and B. L. Pellom, "Growing an n-gram language model," in Proc. Interspeech, 2005.
3. P. F. Brown, V. J. DellaPietra, P. V. deSouza, J. C. Lai, and R. L. Mercer, "Class-based n-gram models of natural language," Computational Linguistics, vol. 18, no. 4, pp. 467-479, 1992.
4. J. Gao, J. T. Goodman, G. Cao, and H. Li, "Exploring asymmetric clustering for statistical language modeling," in Proc. ACL, 2002, pp. 183-190.
5. M. Creutz and K. Lagus, "Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor," Tech. Rep. A81, Publications in Computer and Information Science, Helsinki University of Technology, 2005.
6. T. Hirsimäki, M. Creutz, V. Siivola, M. Kurimo, S. Virpioja, and J. Pylkkönen, "Unlimited vocabulary speech recognition with morph language models applied to Finnish," Computer Speech and Language, 2005, In press, Available online.
7. M. Kurimo, A. Puurula, E. Arisoy, V. Siivola, T. Hirsimäki, J. Pylkkönen, T. Alumäe, and M. Saraclar, "Unlimited vocabulary speech recognition for agglutinative languages," in Proc. HLT-NAACL, 2006.
8. T. R. Niesler and P. C. Woodland, "A variable-length category-based n-gram language model," in Proc. ICASSP, 1996.
9. J. T. Goodman, "A bit of progress in language modeling - extended version," Tech. Rep. MSR-TR-2001-72, Microsoft Research, 2001.
10. M. Siu and M. Ostendorf, "Variable n-grams and extensions for conversational speech language modeling," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 8, no. 1, pp. 63-75, 2000.
11. P. Xu and F. Jelinek, "Random forests in language modeling," in Proc. EMNLP, 2004.
12. A. Pargellis, E. Fosler-Lussier, A. Potamianos, and C.-H. Lee, "A comparison of four metrics for auto-inducing semantic classes," in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, 2001.
13. S. F. Chen, Building Probabilistic Models for Natural Language, Ph.D. thesis, Harvard University, 1996.
14. A. Stolcke, "SRILM - an extensible language modeling toolkit," in Proc. ICSLP, 2002, pp. 901-904.