A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition

Computer Speech and Language

Volumn 21, Issue 1, 2007, Pages 1-25

  Li, Xiaolong ^a   Zhao, Yunxin ^a  

^a University of Missouri   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION TIME; DECODING TIME; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION (LVCSR); ORDER PRESERVING LM CONTEXT PRE COMPUTING (OPCP);

BIT ERROR RATE; CACHE MEMORY; DATA STORAGE EQUIPMENT; MATHEMATICAL MODELS; SPEECH RECOGNITION; VOCABULARY CONTROL;

COMPUTER PROGRAMMING LANGUAGES;

EID: 33749555597     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2005.11.002     Document Type: Article

References (28)

1. Alleva, F., 1997. Search organization in the Whisper continuous speech recognition system. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 295-302.
2. Alleva, F., Huang, X., Hwang, M.-Y., 1996. Improvements on the pronunciation prefix tree search organization. In: Proceedings of ICASSP, Atlanta, GA, USA, vol. 1, pp. 133-136.
3. Aubert, X., 1999. One pass cross word decoding for large vocabularies based on a lexical tree search organization. In: Proceedings of Eurospeech, Budapest, Hungary, vol. 4, pp. 1559-1562.
4. Bryant R., and O'Hallaron D. Computer Systems - A Programmer's Perspective (2003), Pearson Education, Inc.
5. Cardenal-Lopez, A., Dieguez-Tirado, P., Garcia-Mateo, C., 2002. Fast LM look-ahead for large vocabulary continuous speech recognition using perfect hashing. In: Proceedings of ICASSP, Orlando, FL, USA, pp. I-705-I-708.
6. Czech Z., Havas G., and Majewski B. An optimal algorithm for generating minimal perfect hash functions. Information Processing Letters 43 5 (1992) 257-264
7. Deshmukh N., Ganapathiraju A., and Picone J. Hierarchical search for large-vocabulary conversational speech recognition: working towards a solution to the decoding problem. IEEE Signal Processing Magazine 16 5 (1999) 84-107
8. Fox E., Heath L., Chen Q., and Daoud A. Practical minimal perfect hash functions for large databases. Communications of the ACM 35 1 (1992) 105-121
9. Huang X., Acero A., and Hon H. Spoken Language Processing (2001), Prentice-Hall, Englewood Cliffs, NJ
10. Jenkins, R., 1995. Hash Functions for Hash Table Lookup. Available from: .
11. Li, X., Zhao, Y., 2003. Exploiting order-preserving minimum perfect hashing to speedup N-gram language model look-ahead. In: Proceedings of Eurospeech, Geneva, Switzerland, pp. 2281-2284.
12. Martin A., Przybocki, M., 2001. The 2001 NIST evaluation for recognition of conversational speech over the telephone. In: Proceedings of NIST Large Vocabulary Conversational Speech Recognition Workshop, MD, USA. Available from: .
13. Ney H., and Ortmanns S. Dynamic programming search for continuous speech recognition. IEEE Signal Processing Magazine 16 5 (1999) 64-83
14. Ney, H., Welling, L., Ortmanns, S., Beulen, K., Wessel, F., 1998. RWTH large vocabulary continuous speech recognition system. In: Proceedings of ICASSP, Seattle, USA, vol. 2, pp. 853-856.
15. Ortmanns, S., Eiden, A., Ney, H., 1998. Improved lexical tree search for large vocabulary speech recognition. In: Proceedings of ICASSP, Seattle, WA, USA, vol. 2, pp. 817-820.
16. Ortmanns, S., Eiden, A., Ney, H., Coenen, N., 1997. Look-ahead techniques for fast beam search. In: Proceedings of ICASSP, Munich, Germany, pp. 1783-1786.
17. Ortmanns, S., Ney, H., Eiden, A., 1996. Language-model look-ahead for large vocabulary speech recognition. In: Proceedings of ICSLP, Philadelphia, PA, USA, vol. 4, pp. 2095-2098.
18. Sixtus, A., 2003. Across-word phoneme models for large vocabulary continuous speech recognition. Ph.D. dissertation, RWTH, Germany.
19. Sixtus A., and Ney H. From within-word model search to across-word model search in large vocabulary continuous speech recognition. Computer Speech & Language 16 2 (2002) 245-271
20. Soltau, H., Metze, F., Fugen, C., Waibel, A., 2002. Efficient language model lookahead through polymorphic linguistic context assignment. In: Proceedings of ICASSP, Orlando, FL, USA, vol. 1, pp. I-709-I-712.
21. Stolcke, A., 2002. SRILM - An extensible language modeling toolkit. In: Proceedings of International Conference on Spoken Language Processing, Denver, CO, USA, vol. 2, pp. 901-904.
22. Stolcke, A., Bratt, H., Butzberger, J., Franco, H., Gadde, V., Plauche, M., Richey, C., Shriberg, E., Sonmez, K., Weng, F., Zheng, J., 2000. The SRI March 2000 Hub-5 conversational speech transcription system. In: Proceedings of NIST Speech Transcription Workshop, College Park, MD, USA. Available from: .
23. Sundaram, R., Hamaker, J., Picone, J., 2001. Twister: the ISIP 2001 conversational speech evaluation system. In: Proceedings of NIST Large Vocabulary Conversational Speech Recognition Workshop, Linthicum Heights, MD, USA. Available from: .
24. Tarjan, R., 1983. Data Structures and Network Algorithms. SIAM Monograph #44.
25. Woodland, P., Evermann, G., Gales, M., Hain, T., Liu, A., Moore, G., Povey, D., Wang, L., 2002. CU-HTK April 2002 Switchboard System. In: Proceedings of NIST Rich Transcription Workshop, Vienna, VA, USA. Available from: .
26. Young S., Kershaw D., Odell J., Allison D., Valtchev V., and Woodland P. The HTK Book Version 3.0 (2000), Cambridge University, Cambridge, England
27. Young, S., Russel, R., Thornton, J., 1989. Token passing: A simple conceptual model for connected speech recognition systems. Technical Report, Cambridge University Engineering Department.
28. Zhang, X., Zhao Y., 2002. Minimum perfect hashing for fast N-gram language model lookup. In: Proceedings of ICSLP, Denver, CO, USA, vol. 1, pp. 401-404.