Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard)

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Huang, J ^a   Kingsbury, B ^a   Mangu, L ^a   Padmanabhan, M ^a   Saon, G ^a   Zweig, G ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BENCHMARKING; ELECTRIC SWITCHBOARDS; PERSONAL COMMUNICATION SYSTEMS; TRANSCRIPTION;

CONVERSATIONAL SPEECH; DOMAIN INDEPENDENCES; ERROR PERFORMANCE; LARGE VOCABULARY; SPEAKER INDEPENDENTS; SPEECH RECOGNITION PERFORMANCE; TRAINING DATA; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 85009097795     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. M. Padmanabhan, G. Saon, S. Basu, J. Huang, G. Zweig, "Recent improvements on a Voicemail Transcription Task", Proceedings of Eurospeech 1999.
2. Proceedings of the Hub 5 Workshop, 1999.
3. R. O. Duda and P. B. Hart, "Pattern Classification and scene analysis", Wiley, New York, 1973.
4. G. Saon, M. Padmanabhan, R. Gopinath, S. Chen, "Maximum likelihood discriminant feature spaces", Proceedings of ICASSP 2000.
5. R. Gopinath, "Maximum likelihood modeling with Gaussian distributions for classification", Proceedings of ICASSP 1998.
6. G. Zweig and M. Padmanabhan, "Boosting Gaussian mixtures in an LVCSR system", Proceedings of ICASSP 2000.
7. Y. Freund and R. Schapire, "Experiments with a new boosting algorithm", Proceedings of Intl Conference on Machine Learning, July 1996, Morgan Kaufman.
8. R. Schapire, Y. Freund, P. Bartlett, W. S. Lee, "Boosting the margin: A new explanation for the effectiveness of voting methods", Annals of Statistics, 26(5):1651-1686, 1998.
9. L. Mangu, E. Brill and A. Stolcke, "Finding consensus among words: lattice-based word error minimization", Proceedings of Eurospeech 1999.
10. J. G. Fiscus, "A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER) ", Proceedings of IEEE ASRU Workshop, pp. 347-352, Santa Barbara, 1997.
11. B. E. D. Kingsbury, N. Morgan and S. Greenberg, "Robust speech recognition using the modulation spectrogram", Speech Communication, 25(1-3), pp 117-132, 1998.