Applications of virtual-evidence based speech recognizer training

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 2562-2565

  Subramanya, Amarnag ^a   Bilmes, Jeff ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

Dynamic Bayesian networks; Speech recognition; Virtual evidence

Indexed keywords

DOMAIN KNOWLEDGE; DYNAMIC BAYESIAN NETWORK; PHONE RECOGNITION; RELATIVE ERROR RATES; SPEECH RECOGNIZER; TRAINING ALGORITHMS; VIRTUAL-EVIDENCE;

BAYESIAN NETWORKS; CONTINUOUS SPEECH RECOGNITION; DISTRIBUTED PARAMETER NETWORKS; INFERENCE ENGINES; INTELLIGENT NETWORKS; TELEPHONE SETS; TELEPHONE SYSTEMS;

SPEECH COMMUNICATION;

EID: 84867197731     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. A. Subramanya and J. Bilmes, "Virtual Evidence for training Speech Recognizers using partially labeled data," in Human Language Technologies Conference (HLT-NAACL), 2007.
2. A. Subramanya, C. Bartels, J. Bilmes and P. Nguyen, "Uncertainty in training Large Vocabulary Speech Recognizers," in Proc. of ASRU, 2007.
3. G. Evermann, H. Y. Chan and M.J.F. Gales, "Training LVCSR systems on thousands of hours of data," in Proc. of ICASSP, 2000.
4. A. Stolcke et al., "The SRI March 2000 Hub-5 conversational speech transcription system," in Proc. of NIST Speech Transcription Workshop, 2000.
5. L. Lamel, J. Gauvian and G. Adda, "Lightly supervised and unsupervised acoustic model training," in Computers, Speech and Language, 2002.
6. J. Bilmes, "On Soft Evidence in Bayesian networks," Tech. Rep. UWEETR-2004-0016, Univ. of Washington, Dept. of EE, 2004.
7. J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann Publishers, Inc., 1988.
8. K. F. Lee and H. Hon, "Speaker independent phone recognition using hidden markov models," IEEE Transactions on Acoustics, Speech and Signal Processing, 37(11), 1989.
9. J. Glass, J. Chang and M. McCandless, "A Probabilistic Framework for Feature-based Speech Recognition," in Proc. of ICSLP, 1996.
10. J. Godfrey, E. Holliman and J. McDaniel, "Switchboard: Telephone speech corpus for research and development," in Proc. of ICASSP, 1992, vol. 1, pp. 517-520.
11. S. King, C. Bartels and J. Bilmes, "SVitchboard: Small-vocabulary tasks from switchboard," in Proc. of the European Conf. on Speech Communication and Technology, 2005.
12. K. Livescu et al., "Articulatory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU summer workshop," in Proc. of ICASSP, 2007.
13. C. Bartels and J. Bilmes, "Use of Syllable Nuclei Locations to Improve ASR," in Proc. of IEEE ASRU, 2007.
14. N. Deshmukh et al., "Re-segmentation of switchboard," in Proc. of ICSLP, Sydney, Australia, November 1998, pp. 1543-1546.
15. J. Bilmes, GMTK: The Graphical Models Toolkit, 2002.
16. M. Box, "A New Method of Constrained Optimization and a comparison with Other Methods," in Computer Journal, 1965.
17. A. Bordes, S. Ertekin, J. Weston and L. Bottou, "Fast kernel classifiers with online and active learning" in Proc. of JMLR, 6, 2005.