An overview of decoding techniques for large vocabulary continuous speech recognition

Computer Speech and Language

Volumn 16, Issue 1, 2002, Pages 89-114

  Aubert, Xavier L ^a  

^a PHILIPS RESEARCH LABORATORIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC TRANSDUCERS; ALGORITHMS; DECODING; FINITE AUTOMATA; HEURISTIC METHODS; SPEECH RECOGNITION;

CROSS-WORD PHONETIC CONTEXTS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; M-GRAM LANGUAGE MODELS; SEARCH SPACE REPRESENTATION; WEIGHTED FINITE STATE TRANSDUCERS;

SPEECH CODING;

EID: 0036460898     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.2001.0185     Document Type: Article

References (54)

1. Aho, A. V., Hopcroft, J. E. & Ullman, J. D. (1974). The Design and Analysis of Computer Algorithms. Addison Wesley.
2. Alleva, F., Huang, X. & Hwang, M.-Y. (1996). Improvements on the pronunciation prefix tree search organization. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Atlanta, GA, pp. 133-136.
3. Alleva, F. (1997). Search organization in the whisper continuous speech recognition system. Proceedings of the IEEE ASRU Workshop, Santa Barbara, CA, pp. 295-302
4. Antoniol, G., Brugnara, F., Cettolo, M. & Frederico, M. (1995). Language model representations for beam-search decoding. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Detroit, MI, pp. 588-591.
5. Aubert, X. & Ney, H. (1995). Large vocabulary continuous speech recognition using word graphs. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Detroit, MI, USA, pp. 49-52.
6. Aubert, X. (1999). One pass cross word decoding for large vocabularies based on a lexical tree search organization. Proceedings of the European Conference on Speech Communication and Technology, Budapest, Hungary, pp. 1559-1562.
7. Aubert, X. & Blasig, R. (2000). Combined acoustic and linguistic look-ahead for one-pass time-synchronous decoding. Proceedings of the International Conference on Spoken Language Processing, volume 3, Bejing, China, pp. 802-805.
8. Bahl, L. R., Jelinek, F. & Mercer, R. L. (1983). A maximum likelihood approach to continuous speech recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence, volume 5, pp. 179-190.
9. Bazzi, I. & Glass, J. (2000). Heterogeneous lexical units for automatic speech recognition: preliminary investigations. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey, pp. 1257-1260.
10. Bellman, R. E. (1957). Dynamic Programming. Princeton University Press, Princeton, NJ.
11. Bertoldi, N., Brugnara, F., Cettolo, M., Frederico, M. & Giuliani, D. (2001). From broadcast news to spontaneous dialogue transcription: portability issues. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Salt Lake City, Utah, USA, pp. 37-40.
12. Boulianne, G., Brousseau, J., Ouellet, P. amp; Dumouchel, P. (2000). French large vocabulary recognition with crossword phonology transducers. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey, pp. 1675-1678.
13. DARPA (2000). Dec'99 evaluation of 10x real-time transcriptions of broadcast news. DARPA Proceedings of the Broadcast News Workshop, Morgan Kaufmann Publishers, San Francisco.
14. Demuynck, K., Duchateau, J. & Van Compernolle, D. (1997). A static lexicon network representation for crossword context-dependent phones. Proceedings of the European Conference on Speech Communication and Technology, volume 1, Rhodos, Greece, pp. 143-146.
15. Finke, M., Fritsch, J., Koll, D. & Waibel, A. (1999). Modeling and efficient decoding of large vocabulary conversational speech. Proceedings of the European Conference on Speech Communication and Technology, volume 1, Budapest, Hungary, pp. 467-470.
16. Gauvain, J. L. & Lamel, L. (2000). Fast decoding for indexation of broadcast data. Proceedings of the International Conference on Spoken Language Processing, Volume 3, Beijing, China, pp. 794-797.
17. Gopalakrishnan, P. S., Bahl, L. R. & Mercer, R. L. (1995). A tree search strategy for large-vocabulary continuous speech recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Detroit, WA, pp. 572-575.
18. Hanazawa, K., Yasuhiro, M. & Furui, S. (1997). An efficient search method for large-vocabulary continuous-speech recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume 3, Munich, Germany, pp. 1787-1790.
19. Hochberg, M., Renals, S., Robinson, A. & Kershaw, D. (1994). Large vocabulary continuous speech recognition using a hybrid connectionist-HMM system. Proceedings of the International Conference on Spoken Language Processing, Yokohama, Japan, pp. 1499-1502.
20. Jelinek, F., Bahl, L. R. & Mercer, R. L. (1975). Design of a linguistic statistical decoder for the recognition of continuous speech. IEEE Transactions on Information Theory, IT-21, 250-256.
21. Li, Z., Boulianne, G., Labute, P., Barszcz, M., Garudadri, H. & Kenny, P. (1996). Bi-directional graph search strategies for speech recognition. Computer Speech and Language, 10, 295-321.
22. 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 International Conference on Acoustics, Speech and Signal Processing, WA, Seattle, pp. 665-668.
23. Mohri, M. & Riley, M. (1999). Network optimizations for large-vocabulary speech recognition. Speech Communication Journal, 28, 1-12.
24. Mohri, M., Pereira, F., Riley, M. & AT&T Labs Research, (2000). Weighted finite-state transducers in speech recognition. ASR '2000 Proceedings, Paris, France, pp. 97-106.
25. Neukirchen, C., Aubert, X. & Dolfing, H. (2000). Extending the generation of word graphs for a cross-word M-gram decoder. Proceedings of the International Conference on Spoken Language Processing, volume 4, Bejing, China, pp. 302-305.
26. Ney, H., Mergel, D., Noll, A. & Paeseler, A. (1987). A data driven organization of the dynamic programming beam search for continuous speech recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Dallas, Texas, pp. 833-836.
27. (1992) Also in IEEE Transaction on Signal Processing, SP-40. 272-281.
28. Ney, H., Haeb-Umbach, R., Tran, B. H. & Oerder, M. (1992). Improvements in beam search for 1000-word continuous speech recognition, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, volume I, San Francisco, CA, pp. 9-12.
29. Ney, H., Ortmanns, S. & Lindam, I. (1997). Extensions to the word graph method for large vocabulary continuous speech recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Munich, pp. 1787-1790.
30. Nguyen, L. & Schwartz, R. (1998). The BBN single-phonetic-tree fast-match algorithm. Proceedings of the International Conference on Spoken Language Processing, Sydney, Australia, pp. 1827-1830.
31. Nilsson, N. J. (1998). Artificial Intelligence: A New Synthesis. Morgan Kaufmann Publishers, Inc., San Francisco, CA.
32. Novak, M. & Picheny, M. (1999). Speed improvement of the time-asynchronous acoustic fast match. Proceedings of the European Conference on Speech Communication Technology '99, Budapest, Hungary, pp. 1115-1118.
33. 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, pp. 405-410.
34. Oerder, M. & Ney, H. (1993). Word graphs: an efficient interface between continuous speech recognition and language understanding. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume 2, Minneapolis, MN, pp. 119-122.
35. Ortmanns, S., Ney, H. & Eiden, A. (1996). Language-model look-ahead for large vocabulary speech recognition. Proceedings of the International Conference on Spoken Language Processing 96, Philadelphia, pp. 2095-2098.
36. Ortmanns, S., Ney, H., Seide, F. & Lindam, I. (1996). A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition. Proceedings of the International Conference on Spoken Language Processing, Philadelphia, pp. 2091-2094.
37. Ortmanns, S., Ney, H. & Aubert, X. (1997). A word graph algorithm for large vocabulary continuous speech recognition. Computer Speech and Language, 11, 43-72.
38. Ortmanns, S., Firzlaff, T. & Ney, H. (1997). Fast likelihood computation methods for continuous mixture densities in large vocabulary speech recognition. Proceedings of the European Conference on SpeechCommunication and Technology '97, Rhodes, Greece, pp. 139-142.
39. Ortmanns, S., Reichl, W. & Chou, W. (1999). An efficient decoding method for real-time speech recognition. Proceedings of the European Conference on Speech Communication and Technology, Budapest, Hungary, pp. 499-502.
40. Ortmanns, S. & Ney, H. (2000). The time-conditioned approach in dynamic programming search for LVCSR. IEEE Transaction of Speech and Audio Processing, 8, 676-687.
41. Paul, D. B. (1992). An efficient A* decoder algorithm for continuous speech recognition with a stochastic language model. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume 1, CA, pp. 25-28.
42. Pereira, F., Riley, M. & Sproat, R. (1994). Weighted rational transductions and their application to human language processing. Proceedings of the ARPA HLT Workshop.
43. Placeway, P., Schwartz, R., Fung, P. & Nguyen, L. (1993). The estimation of powerful language models from small and large corpora. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume II, Minneapolis, MN, USA, pp. 33-36.
44. Renals, S. & Hochberg, M. (1999). Start-synchronous search for large vocabulary continuous speech recognition. IEEE Transactions on Speech and Audio Processing, 7, 542-553.
45. Robinson, T. & Christie, J. (1998). Time-first search for large vocabulary speech recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Seattle, USA, pp. 829-832.
46. Schramm, H. & Aubert, X. (2000). Efficient integration of multiple pronunciations in a large vocabulary decoder. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume 3, Istanbul, Turkey, pp. 1659-1662.
47. Schuster, M. (2000). Memory-efficient LVCSR search using a one-pass stack decoder. Computer Speech and Language, 14, pp. 47-77.
48. Schwartz, R. & Austin, S. (1991). A comparison of several approximate algorithms for finding multiple (N-BEST) sentence hypotheses. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada, pp. 701-704.
49. Seide, F. (2001). The use of virtual hypothesis copies in decoding of large-vocabulary continuous speech. Philips Research East-Asia, submitted to IEEE Transactions on Speech and Audio Processing, Taipei.
50. 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 International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey, pp. 1671-1674.
51. Steinbiss, V. (1991). A search organization for large vocabulary recognition based on N-best decoding. Proceedings of the European Conference on Speech Communication and Technology, Genova, Italy, pp. 1217-1220.
52. Steinbiss, V., Tran, B. H. & Ney, H. (1994). Improvements in beam search. Proceedings of the International Conference on Spoken Language Processing, Yokohama, Japan, pp. 2143-2146.
53. Willett, D., Neukirchen, C. & Rigoll, G. (2000). Ducoder-the Duisburg University LVCSR stack decoder. Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey, pp. 1555-1558.
54. Young, S. J., Russel, N. H. & Thornton, J. H. (1989). Token passing: a simple conceptual model for connected speech recognition systems. Technical Report F_INFENG/TR38, Cambridge University Engineering Department.