Constructing ensembles of asr systems using randomized decision trees

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn I, Issue , 2005, Pages

  Siohan, Olivier ^a   Ramabhadran, Bhuvana ^a   Kingsbury, Brian ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; AUTOMATION; DECISION THEORY; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH INTELLIGIBILITY;

AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS; DECISION TREES; ERROR RATE; VOCABULARY RECOGNITION;

SPEECH RECOGNITION;

EID: 33646818291     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415084     Document Type: Conference Paper

References (20)

1. T. G. Dietterich, "Ensemble methods in machine learning," Lecture Notes in Computer Science, vol. 1857, pp. 1-15, 2000.
2. L. K. Hansen and P. Salamon, "Neural network ensemble," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 12, pp. 993-1001, 1990.
3. L. Breiman, "Bagging predictors," Machine Learning, vol. 24, no. 2, pp. 123-140, 1996.
4. Y. Freund and R. E. Schapire, "Experiments with a new boosting algorithm," in Proc. of the Thirteenth Int. Conf. on Machine Learning, 1996.
5. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recogniser output voting error reduction (ROVER)," in Proc. IEEE ASRU Workshop, Santa Barbara, 1997, pp. 347-352.
6. P. Niyogi, J.-B. Pierrot, and O. Siohan, "Multiple classifiers by constrained minimization," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Istanbul, Turkey, 2000.
7. H. Schwenk, "Using boosting to improve a hybrid HMM/neural network speech recognizer," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Phoenix, Arizona, USA, 1999, vol. 2, pp. 1009-1012.
8. C. Dimitrakakis and S. Bengio, "Boosting HMMs with an application to speech recognition," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Montreal, Canada, 2004.
9. G. Zweig and M. Padmanabhan, "Boosting gaussian mixtures in an LVCSR system," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Istanbul, Turkey, 2000, vol. 3, pp. 1527-1530.
10. L. Breiman, "Random forests - random features," Tech. Rep. 567, Statistics Department, U. C. Berkeley, Sept. 1999, ftp://ftp.stat.berkeley.edu/ pub/users/breiman.
11. W. Byrne, D. Doermann, M. Franz, S. Gustman, J. Hajič, D. Oard, M. Picheny, J. Psutka, B. Ramabhadran, D. Soergel, T. Ward, and W.-J. Zhu, "Automatic recognition of spontaneous speech for access to multilingual oral history archives," IEEE Transactions on Speech and Audio Processing, vol. 12, no. 4, pp. 420-435, 2004.
12. T. K. Ho, "The random subspace method for constructiong decision forests," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 832-844, Aug. 1998.
13. T. G. Dietterich, "An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, Boosting, and randomization," Machine Learning, vol. 40, no. 2, pp. 139-158, 1998.
14. L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
15. L.R. Bahl, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, and M.A. Picheny, "Decision trees for phonological rules in continuous speech," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Toronto, Canada, May 1991, pp. 185-188.
16. W. Reichl and W. Chou, "Robust decision tree state tying for continuous speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 8, no. 5, pp. 555-566, Sept. 2000.
17. L. Breiman, J. Friedman, R.A. Olshen, and C.J. Stone, Classification and Regression Trees, Wadsworth, 1984.
18. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker adaptive training," in Proc. Int. Conf. on Spoken Language Processing, Philadelphia, USA, 1996, pp. 1137-1140.
19. H. Soltau, B. Kingsbury, L. Mangu, D. Povey, G. Saon, and G. Zweig, "The IBM 2004 conversational telephony system for rich transcription in EARS," Submitted to ICASSP'05.
20. M. Bisani and H. Ney, "Bootstrap estimates for confidence intervals in ASR performance evaluation," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Montreal, Canada, 2004, pp. 409-412.