Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion

Computer Speech and Language

Volumn 24, Issue 3, 2010, Pages 433-444

  Yu, Dong ^a   Varadarajan, Balakrishnan ^b   Deng, Li ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

^b JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

Acoustic model; Active learning; Collective information; Confidence; Entropy reduction; Lattice; Semi supervised learning

Indexed keywords

ACOUSTIC MODEL; ACTIVE LEARNING; ENTROPY REDUCTION; INFORMATION CONFIDENCE; SEMI-SUPERVISED LEARNING;

ENTROPY; OPTIMIZATION; SPEECH RECOGNITION; SUPERVISED LEARNING; TRANSCRIPTION;

LEARNING ALGORITHMS;

EID: 77950063604     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2009.03.004     Document Type: Article

References (20)

1. Anderson, B., Moore, A., 2005. Active learning for hidden markov models: objective functions and algorithms. In: ICML 2005.
2. Anderson, B., Siddiqqi, S., Moore, A., 2006. Sequence Selection for Active Learning. Technical Report CMU-IR-TR-06-16.
3. Charlet, D., 2001. Confidence-measure-driven unsupervised incremental adaptation for HMM-based speech recognition. In: Proceedings of ICASSP. pp. 357360.
4. Cohn D., Atlas L., and Ladner R. Improving generalization with active learning, machine learning 15 2 (1994) 201221
5. Dagan, I., Engelson, S.P., 1995. Committee-based sampling for training probabilistic classifiers. In: Proceedings of ICML. pp. 150157.
6. Hakkani-Tr, D., Tur, G., Rahim, M., Riccardi, G., 2004. Unsupervised and active learning in automatic speech recognition for call classification. In: ICASSP 2004.
7. Hakkani-Tur, D., Gorin, A., 2002. Active learning for automatic speech recognition. In: Proceedings of the ICASSP. pp. 39043907.
8. Ji S., Krishnapuram B., and Carin L. Variational bayes for continuous hidden markov models and its application to active learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 28 4 (2006) 522-532
9. Kamm, T.M., 2004. Active Learning for Acoustic Speech Recognition Modeling, Ph.D. Thesis. The Johns Hopkins University, Baltimore.
10. Kamm, T.M., Meyer, G.G.L., 2003. Word-selective training for speech recognition. In: Proceedings of the IEEE Workshop ASRU.
11. Kamm, T.M., Meyer, G.G.L., 2004. Robustness aspects of active learning for acoustic modeling. In: Proceedings of Interspeech, pp. 1095-1098.
12. Kemp, T., Waibel, A., 1999. Unsupervised training of a speech recognizer: recent experiments. In: Proceedings of Eurospeech. pp. 27252728.
13. Kuo, H.-K.J., Goel, V., 2005. Active learning with minimum expected error for spoken language understanding. In: Proceedings of the Interspeech. pp. 437440.
14. Moreno, P.J., Agarwal, S., 2003. An experimental study of em based algorithms for semi-supervised learning in audio classification. In: ICML-2003 Workshop on Continuum from Transcribed to Un-transcribed Data.
15. Riccardi G., and Hakkani-Tur D. Active learning: theory and applications to automatic speech recognition. IEEE Transactions on Speech and Audio Processing 13 4 (2005) 504511
16. Tur G., Hakkani-Tr D., and Schapire R.E. Combining active and semi-supervised learning for spoken language understanding. Journal of Speech Communication 45 2 (2005) 171-186
17. Wessel, F., Macherey, K., Ralf Schluter, 1998. Unsupervised training of a speech recognizer: recent experiments. In: Proceedings of ICASSP. pp. 225228.
18. Yu, D., Ju, Y.-C., Wang, Y.-Y., Zweig, G., Acero, A., 2007. Automated directory assistance system - from theory to practice. In: Proceedings of the Interspeech. pp. 27092712.
19. Zhang, R., Rudnicky, A., 2001. Word level confidence annotation using combinations of features. In: Proceedings of ECSCT. pp. 21052108.
20. Zhang, R., Rudnicky, A.I., 2006. A new data selection approach for semi-supervised acoustic modeling. In: ICASSP. pp. 421424.