Cross-task portability of a broadcast news speech recognition system

Speech Communication

Volumn 38, Issue 3-4, 2002, Pages 335-347

  Bertoldi, N ^a   Brugnara, F ^a   Cettolo, M ^a   Federico, M ^a   Giuliani, D ^a  

^a ITC IRST   (Italy)

Author keywords

Acoustic model adaptation; Language model adaptation; Spontaneous speech phenomena

Indexed keywords

ACOUSTIC WAVES; BROADCASTING; ERROR ANALYSIS; SPEECH CODING;

ADAPTATION METHODS; DOMAIN SPECIFIC BASELINE SYSTEMS;

SPEECH RECOGNITION;

EID: 0036836950     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00074-7     Document Type: Article

References (18)

1. Bertoldi N., Brugnara F., Cettolo M., Federico M., Giuliani D. From broadcast news to spontaneous dialogue transcription: portability issues. Proc. IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, Salt Lake City, UT. 2001.
2. Brugnara F., Cettolo M. Improvements in tree-based language model representation. Proc. 4th Eur. Conf. on Speech Communication and Technology, Madrid, Spain. 1995;2075-2078.
3. Brugnara F., Federico M. Dynamic language models for interactive speech applications. Proc. 5th Eur. Conf. on Speech Communication and Technology, Rhodes, Greece. 1997;2751-2754.
4. Brugnara F., Cettolo M., Federico M., Giuliani D. Advances in automatic transcription of Italian broadcast news. Proc. Internat. Conf. on Spoken Language Processing, Beijing, China. Vol. II:2000;660-663.
5. Cettolo M., Falavigna D. Recognition of spontaneous speech dialogues. Proc. Internat. Conf. on Spoken Language Processing, Sidney, Australia. 1998;1551-1554.
6. Cettolo M., Corazza A., Lazzari G., Pianesi F., Pianta E., Tovena L. A speech-to-speech translation based interface for tourism. Proc. ENTER Conf., Innsbruck, Austria. 1999.
7. Chevalier H., Ingold C., Kunz C., Moore C., Roven C., Yamron J., Baker B., Bamberg P., Bridle S., Bruce T., Weader A. Large-vocabulary speech recognition in specialized domains. Proc. IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, Detroit, MI. Vol. 1:1995;217-220.
8. Dempster A.P., Laird N.M., Rubin D.B. Maximum-likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc., B. 39:1977;1-38.
9. Duda R.O., Hart P.E., Stork D.G. Pattern Classification. 2nd ed. 2001;Wiley, New York.
10. Federico M., Cettolo M., Brugnara F., Antoniol G. Language modeling for efficient beam-search. Comput. Speech Language. 9:1995;353-379.
11. Federico M., Giordani D., Coletti P. Development and evaluation of an Italian broadcast news corpus. Proc. Second Internat. Conf. on Language Resources and Evaluation (LREC), Athens, Greece. Vol. 2:2000;921-924.
12. Gales M.J.F. Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Language. 12:1998;75-98.
13. Jelinek F. Self-organized language modeling for speech recognition. Weibel A., Lee K. Readings in Speech Recognition. 1990;450-505 Morgan Kaufmann, Los Altos, CA.
14. Jelinek F., Mercer R.L., Roukos S. Principles of lexical language modeling for speech recognition. Furui S., Sondhi M.M. Advances in Speech Signal Processing. 1992;651-699 Marcel Dekker, New York.
15. Lefevre F., Gauvain J.-L., Lamel L. Towards task-independent speech recognition. Proc. IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, Salt Lake City, UT. 2001.
16. Leggetter C.J., Woodland P.C. Flexible speaker adaptation for large vocabulary speech recognition. Proc. 4th Eur. Conf. on Speech Communication and Technology, Madrid, Spain. 1995a;1155-1158.
17. Leggetter C.J., Woodland P.C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Language. 9:1995b;171-185.
18. Ney H., Essen U., Kneser R. On structuring probabilistic dependences in stochastic language modelling. Comput. Speech Language. 8:1994;1-38.