Complementary system generation using directed decision trees

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

Volumn 4, Issue , 2007, Pages

  Breslin, C ^a   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Complementary systems; Speech recognition; System combination

Indexed keywords

ALGORITHMS; BIT ERROR RATE; DECISION TREES; LARGE SCALE SYSTEMS; MATHEMATICAL MODELS;

BASELINE SYSTEMS; COMPLEMENTARY SYSTEMS; SYSTEM COMBINATION;

SPEECH RECOGNITION;

EID: 34547541480     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.366918     Document Type: Conference Paper

References (13)

1. J.G. Fiscus, "A post-processing system to yield reduced word error rates: Recogniser output voting error reduction (ROVER)," in Proc. IEEE ASRU Workshop, pages 347-352, 1997.
2. G. Evermann and P. C. Woodland, "Posterior probability decoding, confidence estimation and system combination," in Proceedings Speech Transcription Workshop, College Park, MD, 2000.
3. R. Sinha, M.J.F. Gales, D.Y. Kim, X.A. Liu, K.C. Sim, and P.C. Woodland, "The CU-HTK Mandarin broadcast news transcription system," in Proceedings ICASSP, 2006.
4. M.J.F. Gales, D.Y. Kim, P.C. Woodland, H.Y. Chan, D. Mrva, R. Sinha, and S.E. Tranter, "Progress in the CU-HTK broadcast news transcription system," IEEE Trans. Speech and Audio Processing, vol. 14, pp. 1513-1525, 2006.
5. T.G. Dietterich, "Machine learning research: Four current directions," The AI Magazine, 1997.
6. R. Zhang and A. I. Rudnicky, "A frame level boosting training scheme for acoustic modelling," in Proceedings ICSLP, 2004.
7. C. Meyer, "Utterance-level boosting of HMM speech recognisers," in Proceedings ICASSP, 2002.
8. C. Breslin and M.J.F. Gales, "Generating complementary systems for speech recognition," in Proceedings ICSLP, 2006.
9. L. Breiman, "Bagging predictors," Machine Learning, vol. 24(2), pp. 123-140, 1996.
10. O. Siohan, B. Ramabhadran, and B. Kingsbury, "Constructing ensembles of ASR systems using randomized decision trees," in Proceedings ICASSP, 2005.
11. J. Odell, The use of context in large vocabulary speech recognition, Ph.D. thesis, 1995.
12. L.M. Arslan and J.H.L. Hansen, "Selective Training for Hidden Markov Models with Applications to Speech Classification," IEEE Trans. Speech and Audio Processing, vol. 7, pp. 46-54, 1999.
13. L. Mangu, E. Brill, and A. Stolke, "Finding consensus among words: Lattice-based word error minimization," in Proceedings Eurospeech, 1999.