From within-word model search to across-word model search in large vocabulary continuous speech recognition

Computer Speech and Language

Volumn 16, Issue 2, 2002, Pages 245-271

  Sixtus, Achim ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; ERROR ANALYSIS; MATHEMATICAL MODELS; OPTIMIZATION; SPEECH ANALYSIS; VOCABULARY CONTROL; WORD PROCESSING;

ACOUSTIC PHONEME MODELS; ACROSS WORD MODEL SEARCH; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; WITHIN WORD MODEL SEARCH; WORD GRAPH;

CONTINUOUS SPEECH RECOGNITION;

EID: 0036556171     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.2002.0192     Document Type: Article

References (41)

1. Alleva, F., Hon, H., Huang, X. et al. (1992). Applying SPHINX-II to the DARPA wall street journal CSR task. Proceedings of the DARPA Speech and Natural Language Workshop, Harriman, New York, USA, pp. 393-398.
2. Alleva, F., Huang, X. & Hwang, M. Y. (1993). An improved search algorithm using incremental knowledge for continuous speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, MN, USA. pp. 307-310.
3. Antoniol, G., Brugnara, F., Cettolo, M. & Federico, M. (1995). Language model representations for beam-search decoding. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, USA, pp. 588-591.
4. Aubert, X. L. (1999). One pass crossword decoding for large vocabularies based on a lexical tree search organization. Proceedings of the ISCA European Conference on Speech Communication and Technology, Budapest, Hungary, pp. 91-96.
5. Aubert, X. L. (2000). A brief overview of decoding techniques for large vocabulary continuous speech recognition. Proceedings of the ISCA Automatic Speech Recognition Workshop, Paris, France, pp. 91-96.
6. Aubert, X. L. & Ney, H. Large vocabulary continuous speech recognition using word graphs. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 1, Detroit, MI, USA pp. 49-52.
7. Bahl, L. R., Jelinek, F. & Mercer, R. L. (1983). A maximum likelihood approach to continuous speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5, 179-190.
8. Beulen, K., Bransch, E. & Ney, H. (1997). State-tying for context dependent phoneme models. Proceedings of the ISCA European Conference on Speech Communication and Technology, volume 3, Rhodes, Greece. pp. 1179-1182.
9. Beulen, K., Ortmanns, S. & Elting, C. (1991). Dynamic programming search techniques for across-word modeling in speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, AZ, USA, pp. 609-612.
10. Beyerlein, P., Ullrich, M. & Wilcox, P. (1997). Modeling and decoding of crossword context dependent phones in the PHILIPS large vocabulary continuous speech recognition system. Proceedings of the ISCA European Conference on Speech Communication and Technology, Rhodes, Greece, pp. 1163-1166.
11. Bub, T. & Schwinn, J. (1996), VERBMOBIL: the evolution of a complex large speech-to-speech translation system. Proceedings of the International Conference on Spoken Language Processing, volume 4, Philadelphia, PA, USA, pp. 2371-2374.
12. Demuynck, K., Duchateau, J., Compernolle, D. v. & Wambacq, P. (2000). An efficient search space representation for large vocabulary continuous speech recognition. Speech Communication, 30, 37-53.
13. Demuynck, K., Duchateau, J. & Compernolle, D. v. (1997). A static lexicon network representation for cross-word context dependent phones. Proceedings of the ISCA European Conference on Speech Communication and Technology, Rhodes, Greece, pp. 143-146.
14. Dugast, C., Beyerlein, P. & Haeb-Umbach, R. (1995). Application of clustering techniques to mixture density modeling for continuous speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 1, Detroit, MI, USA, pp. 524-527.
15. Fisher, W. M., Liggett, W. S., Le, A. et al. (1998). Data selection for broadcast news CSR evaluation. Proceedings of the DARPA Broadcast News Transcription and Understanding Workshop, Lansdowne, VA, USA, pp. 12-15.
16. Gauvain, J. L. & Lamel, L. (2000). Fast decoding for indexation of broadcast data. Proceedings of the International Conference on Spoken Language Processing, volume III, Beijing, China, pp. 794-797.
17. Gauvain, J. L., Lamel, L. & Adda-Decker, M. (1995). Developments in continous speech dictation using the ARPA WSJ task. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, USA, pp. 65-58
18. Hwang, M. Y., Hon, H. W. & Lee, K. F. (1989). Modeling between-word coarticulation in continuous speech recognition. Proceedings of the ISCA European Conference on Speech Communication and Technology, Paris, France, pp. 5-8.
19. Jelinek, F. (1976). Continuous speech recognition by statistical methods. Proceedings of the IEEE, 64, 532-556.
20. Kanthak, S., Schütz, K. & Ney, H. (2000a). Using simd instructions for fast likelihood calculation in LVCSR. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, pp. 1531-1534.
21. Kanthak, S., Sixtus, A., Molau, S. & Ney, H. (2000b). Within-word vs. across-word decoding for online speech recognition. Proceedings of the ISCA Automatic Speech Recognition Workshop, Paris, France, pp. 40-45.
22. Lee, K. F., Hon, H. W., Hwang, M. Y., Mahajan, S. & Reddy, R. (1989). The SPHINX speech recognition system. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Glasgow, Scotland, UK, pp. 445-448.
23. Mohri, M., Pereira, F. & Riley, M. (2000). Weighted finite-state transdurcers in speech recognition. Proceedings of the ISCA Automatic Speech Recognition Workshop, Paris, France, pp. 97-106.
24. Neukirchen, C., Aubert, X. L. & Dolfing, H. (2000). Extending the generation of word graphs for a crossword m-gram decoder. Proceedings of the International Conference on Spoken Language Processing, Volume IV, Beijing, China, pp. 302-305.
25. Ney, H., Haeb-Umbach, R., Tran, B.-H. & Oerder, M. (1992). Improvements in beam search for 10000-word continuous speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 1, San Francisco, CA, USA, pp. 9-12.
26. Nguyen, L. & Schwartz, R. (1997). Efficient 2-pass N-best decoder. Proceedings of the ISCA European Conference on Speech Communication and Technology, Rhodes, Greece, pp. 167-170.
27. Odell, J. J. (1995). The use of context in large vocabulary speech recognition. PhD Thesis, University of Cambridge, Cambridge, UK.
28. Odell, J. J., Valtchev, V., Woodland, P. C. & Young, S. J. (1994). A one-pass decoder design for large vocabulary recognition. Proceedings of the ARPA Spoken Language Technology Workshop, Plainsboro, NJ, USA, pp. 405-410.
29. Ortmanns, S., Ney, H. & Aubert, X. L. (1997). A word graph algorithm for large vocabulary continuous speech recognition. Computer Speech and Language, 11, 43-72.
30. Ortmanns, S., Ney, H., Eiden, A. & Coenen, N. (1996). Look-ahead techniques for improved beam search. Proceedings of the CRIM-FORWISS Workshop, Montreal, Canada, pp. 10-22.
31. Ortmanns, S., Reichl, W. & Chou, W. (1999). An efficient decoding method for real time speech recognition. Proceedings of the ISCA European Conference on Speech Communication and Technology, Budapest, Hungary, pp. 499-502.
32. Pallett, D. S., Fiscus, J. G., Fisher, W. M., Garofolo, J. S., Lund, B. A. & Przybocki, M. A. (1995). 1994 Benchmark test for the ARPA spoken language program. Proceedings of the ARPA Human Language Technology Workshop, Austin, TX, USA, pp. 5-36.
33. Paul, D. B. (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, USA, pp. 25-28.
34. Ravishankar, M. K. (1996). Efficient algorithms for speech recognition. PhD Thesis, Carnegie Mellon University, Pittsburgh, PA, USA.
35. Reichl, W. & Chou, W. (1999). A unified approach of incorporating general features in decision tree based acoustic modeling. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, AZ, USA, pp. 573-576.
36. Schramm, H. & Aubert, X. L. (2000). Efficient integration of multiple pronunciations in a large vocabulary decoder. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, pp. 2169-2172.
37. Schwartz, R. & Austin, S. (1991). A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Volume 1, Toronto, Canada, pp. 701-704.
38. Schwartz, R., Austin, S., Kubala F. et al. (1992). New uses for the N-best sentence hypotheses within the BYBLOS speech recognition system. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 1, San Francisco, CA, USA, pp. 1-4.
39. Sixtus, A., Molau, S., Kanthak, S., Schlüter, R. & Ney, H. (2000). Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 3, Istanbul, Turkey, pp. 1671-1674.
40. Sixtus, A. & Ortmanns, S. (1999). High quality word graphs using forward-backward pruning. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Volume 2, Phoenix, AZ, USA, pp. 593-596.
41. Steinbiss, V., Tran, B. H. & Ney, H. (1994). Improvements in beam search. Proceedings of the International Conference on Spoken Language Processing, Volume 4, Yokohama, Japan, pp. 2143-2146.