Directed decision trees for generating complementary systems

Speech Communication

Volumn 51, Issue 3, 2009, Pages 284-295

  Breslin, C ^a   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Complementary systems; Speech recognition; System combination

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DECISION THEORY; DECISION TREES; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH RECOGNITION;

BROADCAST NEWS; COMPLEMENTARY SYSTEMS; CONFUSION NETWORKS; DECISION TREE GENERATIONS; DIRECTED TREES; DIVERGENCE MEASURES; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITIONS; MULTIPLE SYSTEMS; NEW ALGORITHMS; SYSTEM COMBINATION;

TREES (MATHEMATICS);

EID: 58149202339     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2008.09.004     Document Type: Article

References (43)

1. Arslan L., and Hansen J. Selective training for hidden markov models with applications to speech classification. IEEE Trans. Speech Audio Process. 7 (1999) 46-54
2. Breiman L. Bagging predictors. Mach. Learn. 24 2 (1996) 123-140
3. Breiman L. Random forests. Mach. Learn. 45 (2001) 5-32
4. Breslin, C., Gales, M., 2006. Generating complementary systems for speech recognition. In: Proc. ICSLP.
5. Breslin, C., Gales, M., 2007a. Building multiple complementary systems using directed decision trees. In: Proc. interspeech.
6. Breslin, C., Gales, M., 2007b. Generating complementary systems using directed decision trees. In: Proc. ICASSP.
7. Buckwalter, T., 2004. Buckwalter Arabic morphological analyzer version 2.0. LDC2004L02, Linguistic Data Consortium.
8. Cincarek T., Toda T., Saruwatari H., and Shikano K. Utterance based selective training for the automatic creation of task dependent acoustic models. IEICE Trans. Info Systems 89 3 (2006) 962-969
9. Dietterich T. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting and randomization. Mach. Learn. 12 (1999) 1-22
10. Dietterich T. Ensemble methods in machine learning. Lect. Notes Comput. Sci. 1857 (2000) 1-15
11. Dimitrakakis, C., Bengio, S., 2004. Boosting HMMs with an application to speech. In: Proc. ICASSP.
12. Evermann, G., Woodland, P.C., 2000. Posterior probability decoding, confidence. In: Proc. Speech Transcription Workshop.
13. Fiscus, J., 1997. A post-processing system to yield reduced word error rates: recogniser output voting error reduction (ROVER). In: Proc. IEEE ASRU Workshop.
14. Freund, Y., Schapire, R., 1996. Experiments with a new boosting algorithm. In: Proc. of the 13th Internat. Conf. on Mach. Learn.
15. Gales, M., Diehl, F., Raut, C., Tomalin, M., Woodland, P., Yu, K., 2007. Development of a phonetic system for large vocabulary Arabic speech recognition. In: Proc. ASRU.
16. Gales M., Kim D., Woodland P., Chan H., Mrva D., Sinha R., and Tranter S. Progress in the CU-HTK broadcast news transcription system. IEEE Trans. Speech Audio Process. 14 (2006) 1513-1525
17. Gauvain J., Lamel L., and Adda G. The LIMSI broadcast news transcription system. Speech Comm. 37 1-2 (2002) 89-108
18. Gillick, L., Cox, S., 1989. Some statistical issues in the comparison of speech recognition algorithms.
19. Hain, T., Burget, L., Dines, J., Garau, G., Wan, V., Karafiat, M., Vepa, J., Lincoln, M., 2007. The AMI system for the transcription of speech in meetings.
20. Hoffmeister, B., Klein, T., Schluter, R., Ney, H., 2006. Frame based system combination and a comparison with weighted ROVER and CNC. In: Proc. ICSLP.
21. Hu, R., Zhao, Y., 2007. A Bayesian approach for phonetic decision tree state tying in conversational speech recognition. In: Proc. ICASSP.
22. Huang, J., Marcheret, E., Visweswariah, K., Libal, V., Potamianos, G., 2007. Detection, diarization and transcription of far-field lecture speech. In: Proc. Interspeech.
23. Hwang, M., Wang, W., Lei, X., Zheng, J., Cetin, O., Peng, G., 2007. Advances in Mandarin broadcast speech recognition.
24. Jiang H. measures for speech recognition: a survey. Speech Comm. 45 (2005) 455-470
25. Kamm, T., Meyer, G., 2003.Word-selective training for speech recognition. In: Proc. IEEE Workshop on Automatic Speech Recognition and Understanding.
26. Kullback S., and Leibler R. On information and sufficiency. Ann. Math. Statist. 22 (1951) 79-86
27. Lamel L. Lightly supervised and unsupervised acoustic model training. Comp., Speech Lang (2002)
28. Mangu,L., Brill, E., Stolke, A., 1999. Finding consensus among words: lattice-based word error minimization. In: Proc. Eurospeech.
29. Meyer, C., 2002. Utterance-level boosting of HMM speech recognisers. In: Proc. ICASSP.
30. Nguyen L., Matsoukas S., Davenport J., Kibala F., Schwartz R., and Makhoul J. Progress in transcription of broadcast news using Byblos. Comput., Speech Lang (2002)
31. Nock, H., Gales, M., Young, S., 1997. A comparative study of methods for phonetic decision-tree clustering. In: Proc. Eurospeech.
32. Odell, J., 1995. The use of context in large vocabulary speech recognition, Ph.D. thesis, University of Cambridge.
33. Povey, D., 2005. Discriminative training for large vocabulary speech recognition, Ph.D. thesis, University of Cambridge.
34. Ramabhadran, B., Siohan, O., Mangu, L., Zweig, G., Westphal, M., Schulz, H., Soneiro, A., 2006. The IBM 2006 speech transcription system for European parliamentary.
35. Rand W.M. Objective criteria for the evaluation of clustering methods. J. Amer. Statist. Assoc. 66 (1971) 846-850
36. Schwenk, H., 1999. Using boosting to improve a hybrid hmm/neural-network speech recogniser. In: Proc. ICASSP.
37. Sinha, R., Gales, M., Kim, D., Liu, X., Sim, K., Woodland, P., 2006. The CU-HTK Mandarin broadcast news transcription system. In: Proc. ICASSP.
38. Siohan, O., Ramabhadran, B., Kingsbury, B., 2005. Constructing ensembles of ASR systems using randomized decision trees. In: Proc. ICASSP.
39. Stuker, S., Fugen, C., Burger, S., Wolfel, M., 2006. Cross-system adaptation and combination for continuous speech recognition: the influence of phoneme set and acoustic front-end. In: Proc. ICSLP.
40. Xue, J., Zhao, Y., 2007. Novel lookahead decision tree state tying for acoustic modelling. In: Proc. ICASSP.
41. Zhang, R., Rudnicky, A., 2004. A frame level boosting training scheme for acoustic modelling. In: Proc. ICSLP.
42. Zhang, R., Rudnicky, A.I., 2003. Improving the performance of an LVCSR system through ensembles of acoustic models. In: Proc. ICASSP.
43. Zweig, G., Padmanabhan,M., 2000. Boosting Gaussian mixtures in an LVCSR system. In: Proc. ICASSP.