Multilingual large vocabulary speech recognition: The European SQALE project

Computer Speech and Language

Volumn 11, Issue 1, 1997, Pages 73-89

  Young, S J ^a   Adda Dekker, M ^b   Aubert, X ^c   Dugast, C ^c   Gauvain, J L ^b   Kershaw, D J ^a   Lamel, L ^b   Leeuwen, D A ^d   Pye, D ^a   Robinson, A J ^a   Steeneken, H J M ^d   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b CNRS   (France)

^c PHILIPS RESEARCH LABORATORIES   (Germany)

^d TNO   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER AIDED LANGUAGE TRANSLATION; PATTERN RECOGNITION SYSTEMS; SPEECH ANALYSIS;

SOFTWARE PACKAGE SQALE;

SPEECH RECOGNITION;

EID: 0030718943     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1996.0023     Document Type: Article

References (34)

1. Aubert, X. & Dugast, C. (1995). Improved acoustic-phonetic modeling in the Philips' dictation system by handling liaisons and multiple pronunciations. Proceedings of Eurospeech, pp. 767-770, Madrid, Spain.
2. Aubert, X. & Ney, H. (1995). Large vocabulary continuous speech recognition using word graphs. Proceedings of ICASSP, Vol 1, pp. 49-52, Detroit, MI, U.S.A.
3. Bahl, L. R., Balakrishnan-Aiyer, S., Bellegarda, J. R., Franz, M., Gopalakrisnan, P. S., Nahamoo, D., Novak, M., Padmanabhan, M., Picheny, M. A. & Roukos, S. (1995). Performance of the IBM large vocabulary continuous speech recognition system on the ARPA. Wall Street Journal task. Proceedings of ICASSP, Vol 1, pp. 41-44, Detroit, MI, U.S.A.
4. Davis, S. B. & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions of ASSP, 28, 357-366.
5. Dugast, C., Aubert, X. & Kneser, R. (1995). The Philips large-vocabulary recognition system for American English, French and German. Proceedings of Eurospeech, pp. 197-200, Madrid, Spain.
6. Dugast, C., Kneser, R., Aubert, X., Ortmanns, S., Beulen, K. & Ney, H. (1995). Continuous speech recognition tests and results for the NAB'94 corpus. Proceedings of the Spoken Language Technology Workshop, pp. 156-161, Austin, TX, U.S.A.
7. Eskenazi, M., Mariani, J. & Bornerand, S. (1991). Report on the ICSLP satellite workshop on assessment in Kobe (Japan) and visits to several Japanese laboratories working on speech communication, 19-30 November 1990. Speech Communication, 10.
8. Fransen, J., Pye, D., Robinson, A. J., Woodland, P. C. & Young, S. J. (1994). WSJCAM0 corpus and recording description. CUED Technical Report, CUED/F-INFENG/TR.192.
9. Gauvain, J.-L., Lamel, L. & Adda-Decker, M. (1995). Developments in large vocabulary dictation: the LIMSI Nov 94 NAB system. Proceedings of the Spoken Language Technology Workshop, pp. 131-138, Austin, TX, U.S.A.
10. Gauvain, J.-L., Lamel, L., Adda, G. & Adda-Decker, M. (1994). Continuous speech dictation in French. Proceedings of International Conference Spoken Language Processing, ICSLP, Yokohama, Japan.
11. Geutner, P. (1995). Using morphology toward better large vocabulary speech recognition systems. Proceedings of the ICASSP, Vol 1, pp. 445-448, Detroit, MI, U.S.A.
12. Gillick, L. & Cox, S. (1989). Statistical significance tests for speech recognition algorithms. Proceedings of ICASSP, pp. 532-535, Glasgow, U.K.
13. Haeb-Umbach, R., Geller, D. & Ney, H. (1993) Improvements in connected digit recognition using linear discriminant analysis and mixture densities. Proc ICASSP, Vol II, pp. 239-242, Minneapolis.
14. Hays, W. L. (1963). Statistics. London: Holt, Rinehart and Winston.
15. Hermansky, H. (1990). Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of the Acoustical Society of America, 87, 1783-1752.
16. Hochberg, M., Renals, S. & Robinson A. (1995). ABBOT: the CUED hybrid connectionist-HMM large vocabulary recognition system. Proceedings of the Spoken Language Technology Workshop, pp. 170-178, Austin, TX, U.S.A.
17. Kershaw, D. J., Hochberg, M. M. & Robinson, A. J. Context dependent classes in a hybrid recurrent network-HMM speech recognition system. Cambridge University Engineering Department, Technical Report, CUED/F-INFENG/TR.217.
18. Kubala, F., Bellegarda, J., Cohen, J., Pallett, D., Paul, D., Phillips, M., Rajesekaran., R. Richardson, F., Riley, M., Rosenfeld, R., Roth, R. & Weintraub, M. (1994). The hub and spoke paradigm for CSR evaluation. Proceedings of the Spoken Language Technology Workshop, Plainsboro, NJ, U.S.A.
19. Lamel, L. F., Gauvain, J.-L. & Eskanazi, M. (1991). BREF, a large vocabulary spoken corpus for French. Proceedings of Eurospeech '91, Genoa, Italy.
20. Lamel, L., Adda-Decker, M. & Gauvain, J.-L. (1995). Issues in large vocabulary multilingual speech recognition. Proceedings of Eurospeech, pp. 185-188, Madrid, Spain.
21. Leggetter, C. J. & Woodland, P. C. (1995). Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language, 9, 171-185.
22. Martin, A. (1995). Statistical significance tests for speech recognition benchmark tests. Technical Report, National Institute of Standards and Technology, Gaithersburg, U.S.A.
23. Moore, R. K. (1988). Connected digit recognition in a multilingual environment. RSRE Memo No 4134, Malvern, U.K.
24. Odell, J. J., Valtchev, V., Woodland, P. C. & Young, S. J. (1994). A one-pass decoder design for large vocabulary recognition. Proceedings of the Human Language Technology Workshop, pp. 405-410, Plainsboro, NJ, U.S.A.
25. Pallett, D. S., Fiscus, J. G., Fisher, W. M., Garofolo, J. S., Lund, B. S., Martin, A., Przybocki, M. (1994). The 1993 benchmark tests for the ARPA spoken language program. Proceedings of the Spoken Language Technology Workshop, pp. 15-40, Plainsboro, NJ, U.S.A.
26. Pallett, D. S., Fiscus, J. G., Fisher, W. M., Garofolo, J. S., Lund, B. S., Martin, A., Przybocki, M. (1995). The 1994 benchmark tests for the ARPA spoken language program. Proceedings of the Spoken Language Technology Workshop, pp. 5-38, Austin, TX, U.S.A.
27. Paul, D. B. & Baker, J. M. (1992). The Design for the Wall Street Journal-based CSR corpus. Proceedings of the 5th DARPA Speech and Natural Language Workshop, pp. 357-362, San Mateo, CA: Morgan Kaufmann.
28. Pye, D., Woodland, P. & Young, S. J. (1995). Large vocabulary multilingual speech recognition using HTK. Proceedings of Eurospeech, pp. 181-184, Madrid, Spain.
29. Renals, S. & Hochberg, M. M. (1995). Efficient evaluation of the LVCSR search space using the NOWAY decoder. Proceedings of ICASSP, Vol 1, pp. 149-152.
30. Steeneken, H. J. M. & van Velden, J. G. (1989). Objective and diagnostic assessment of (isolated) word recognizers. Proceedings of ICASSP, pp. 540-543, Glasgow, U.K.
31. Steeneken, H. J. M. & van Leeuwen, D. A. (1995). Multilingual assessment of speaker independent large vocabulary speech recognition systems: the SQALE project. Proceedings of Eurospeech, pp. 1271-1274, Madrid, Spain.
32. van Leeuwen, D. A., van den Berg, L.-G. & Steeneken, H. J. M. (1995). Human benchmarks for speaker independent large vocabulary recognition performance. Proceedings of Eurospeech, pp. 1461-1464, Madrid, Spain.
33. Woodland, P.C., Leggetter, C. J., Odell, J., Valtchev, V. & Young, S. J. (1995). The 1994 HTK large vocabulary speech recognition system. Proceedings of ICASSP, Vol 1, pp. 73-76, Detroit, MI, U.S.A.
34. Young, S. J., Odell, J. J. & Woodland, P. C. (1994). Tree-based state tying for high accuracy acoustic modelling. Proceedings of the Human Language Technology Workshop, pp. 307-312, Plainsboro, NJ, U.S.A.