Memory-efficient LVCSR search using a one-pass stack decoder

Computer Speech and Language

Volumn 14, Issue 1, 2000, Pages 47-77

  Schuster, Mike ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; DECODING; MARKOV PROCESSES; NATURAL LANGUAGE PROCESSING SYSTEMS; PROBABILITY; TABLE LOOKUP;

ACOUSTIC MODEL; N-GRAM LANGUAGE MODEL; ONE PASS STACK DECODER; WORD RECOGNITION;

SPEECH RECOGNITION;

EID: 0033896970     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1999.0135     Document Type: Article

References (39)

1. Alleva, F. (1997). Search organization in the Whisper continuous speech recognition system. Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, CA, pp. 295-302.
2. Alleva, F., Huang, X. & Hwang, M. (1996). Improvements on the pronunciation prefix tree search organization. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Atlanta, GA, volume I, pp. 133-136.
3. Aubert, X., Dugast, C., Ney, H. & Steinbiss, V. (1994). Large vocabulary continuous speech recognition of Wall Street Journal data. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaine, Australia, volume II, pp. 129-132.
4. Bahl, L. R., de Souza, P. V., Gopalakrishnan, P. S., Nahamoo, D. & Picheny, M. (1992). A fast match for continuous speech recognition using allophonic models. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, San Francisco, CA, volume I, pp. I17-I20.
5. Bahl, L. R., De Souza, P. V., Gopalakrishnan, P. S., Nahamoo, D. & Picheny, M. (1993). Word lookahead scheme for cross-word right context models in a stack decoder. Proceedings of the European Conference on Speech Communication and Technology, Berlin, Germany, volume II, pp. 851-854.
6. Beyerlein, P. & Ullrich, M. (1995). Hamming distance approximation for a fast log-likelihood computation for mixture densities. Proceedings of the European Conference on Speech Communication and Technology, Madrid, Spain, volume II, pp. 1083-1086.
7. Bishop, C. M. (1995). Neural Networks for Pattern Recognition, Clarendon Press, Oxford, England.
8. Duda, R. O. & Hart, P. E. (1974). Pattern Classification and Scene Analysis, John Wiley & Sons, New York.
9. Gauvain, J. L., Lamel, L. F., Adda, G. & Adda-Decker, M. (1994). The LIMSI continuous speech dictation system: Evaluation on the ARPA Wall Street Journal task. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, Australia, volume I, pp. 557-560.
10. Gopalakrishnan, P. S. (1995). A tree search strategy for large vocabulary continuous speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Detroit, MI, volume I, pp. 572-575.
11. Gopalakrishnan, P. S. & Bahl, L. R. (1996). Fast matching techniques. In Automatic Speech and Speaker Recognition, Advanced Topics, (Lee, C.-H., Soong, F. K. and Paliwal, K. K., eds), pp. 413-428. Kluwer Academic Publishers, Boston, MA.
12. Hetherington, I. L., Phillips, M. S., Glass, J. R. & Zue, V. W. (1993). A * word network search for continuous speech recognition. Proceedings of the European Conference on Speech Communication and Technology, Berlin, Germany, volume III, pp. 1533-1537.
13. Huang, X. D., Ariki, Y. & Jack, M. A. (1990). Hidden Markov Models for Speech Recognition, Edinburgh University Press, Edinburgh, England.
14. Kawahara, T., Kobayashi, T., Takeda, K., Minematsu, N., Itou, K., Yamamoto, M., Utsuro, T. & Shikano, K. (1998). Sharable software repository for {Japanese} large vocabulary continuous speech recognition. Proceedings of the International Conference on Spoken Language Processing, Sidney, Australia, volume VII, pp. 3257-3260.
15. Kershaw, D. J., Hochberg, M. M. & Robinson, A. J. (1995). Context-dependent Classes in a Hybrid Recurrent Network-hmm Speech Recognition System. Technical Report CUED/F-INGENG/TR217, Cambridge University Engineering Department, Cambridge, England.
16. Mohri, M., Riley, M., Hindle, D., Ljolje, A. & Pereira, F. (1998). Full expansion of context-dependent networks in large vocabulary speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, WA, volume II, pp. 665-668.
17. Murveit, H., Butzberger, J., Digalakis, V. & Weintraub, M. (1993). Large vocabulary dictation using SRI's Decipher™ speech recognition system: Progressive search techniques. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Minneapolis, MN, volume II, pp. 319-322.
18. Neukirchen, C. & Willett, D. Personal communication.
19. Ney, H. (1993). Search strategies for large-vocabulary-continuous-speech recognition. In Speech Recognition and Coding - New Advances and Trends, NATO Advanced Studies Institute, Bubion, Spain, June-July 1993, (Rubio Ayuso, A. and Lopez Soler, J., eds), pp. 210-225. Springer, Berlin.
20. Ney, H. & Aubert, X. (1996). Dynamic programming search: From digit strings to large vocabulary speech recognition. In Automatic Speech and Speaker Recognition, Advanced Topics, (Lee, C.-H., Soong, F. K. and Paliwal, K. K., eds), pp. 385-412. Kluwer Academic Publishers, Boston, MA.
21. Ney, H. & Ortmanns, S. (1997). Progress in dynamic programming search for LVCSR. Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, CA, pp. 287-294.
22. Nilsson, N. J. (1971). Problem Solving Methods of Artificial Intelligence, McGraw Hill, New York.
23. Odell, J. J. (1995). The Use of Context in Large Vocabulary Speech Recognition. PhD Thesis, Cambridge University, Cambridge, England.
24. Ortmanns, S., Ney, H. & Aubert, X. (1997). A word graph algorithm for large vocabulary continuous speech recognition. Computer Speech and Language, 11, 43-72.
25. Paul, D. (1991). Algorithms for an optimal A * search and linearizing the search in the stack decoder. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada, volume I, pp. 693-696.
26. Paul, D. (1992). An efficient A * stack decoder algorithm for continuous speech recognition with a stochastic language model. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, San Francisco, CA, volume I, pp. I-25-I-28.
27. Rabiner, L. & Juang, B. H. (1993). Fundamentals of Speech Recognition, Prentice-Hall, Englewood Cliffs, NJ.
28. Ravishankar, M. K. (1996). Efficient Algorithms for Speech Recognition. PhD Thesis, Carnegie Mellon University, Pittsburgh, PA.
29. Renals, S. & Hochberg, M. (1995a). Decoder Technology for Connectionist Large Vocabulary Speech Recognition. Technical Report CUED/F-INGENG/TR186, Cambridge University Engineering Department, Cambridge, England.
30. Renals, S. & Hochberg, M. (1995b). Efficient search using posterior phone probability estimates. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Detroit, MI, volume I, pp. 596-599.
31. Renals, S. & Hochberg, M. (1996). Efficient evaluation of the search space using the NOWAY decoder. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Atlanta, GA, volume I, pp. 149-153.
32. Robinson, T. & Christie, J. (1998). Time-first search for large vocabulary speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, WA, volume II, pp. 829-833.
33. Robinson, T., Hochberg, M. & Renals, S. (1994). Improved phone modeling with recurrent neural networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaine, Australia, volume I, pp. 37-40.
34. Schuster, M. (1999). On Supervised Learning from Sequential Data with Applications for Speech Recognition. PhD Thesis, Nara Institute of Science and Technology, Nara, JAPAN, (http://isw3.aist-nara.ac.jp/IS/ Shikano-lab/database/library/paper/DT9661205.ps.gz).
35. Schwartz, R., Nguyen, L. & Makhoul, J. (1996). Multiple-pass search strategies. In Automatic Speech and Speaker Recognition, Advanced Topics, (Lee, C.-H., Soong, F. K. and Paliwal, K. K., eds), pp. 429-456. Kluwer Academic Publishers, Boston, MA.
36. Shimizu, T., Yamamoto, H., Masataki, H., Matsunaga, S. & Sagisaka, Y. (1997). Reduction of number of word hypotheses for large vocabulary continuous speech recognition. IEICE Transactions, J79-D-II, 2117-2124. In Japanese.
37. Soong, F. & Huang, E. (1991). A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada, volume I, pp. 705-708.
38. Steinbiss, V., Tran, B. & Ney, H. (1994). Improvements in beam search. Proceedings of the International Conference on Spoken Language Processing, Yokohama, Japan, pp. S36-5.1-S36-5.4.
39. Young, S., Jansen, J., Odell, J., Ollason, D. & Woodland, P. The HTK Book, Version 2.1 (distributed with the HTK toolkit).