Dirichlet mixture models of neural net posteriors for HMM-based speech recognition

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

Volumn , Issue , 2011, Pages 5028-5031

  Balakrishnan, V ^a   Sivaram, G S V S ^a   Khudanpur, Sanjeev ^a  

^a JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

Dirichlet distribution; HMMs; neural network posteriors

Indexed keywords

CONVENTIONAL APPROACH; DIRICHLET DISTRIBUTIONS; DIRICHLET MIXTURE MODEL; EXPONENTIAL FAMILY; GAUSSIAN MIXTURE MODELS; HMMS; NEURAL NET; NOVEL TECHNIQUES; PHONEME RECOGNITION; POSTERIOR PROBABILITY; PROBABILITY VECTOR;

NEURAL NETWORKS; PROBABILITY DISTRIBUTIONS; SIGNAL PROCESSING; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 80051614108     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947486     Document Type: Conference Paper

References (11)

1. D.M. Titterington, Statistical Analysis of Finite Mixture Distributions, vol. 1, Wiley Series in Probability and Statistics.
2. A.P. Dempster, N.M. Laird, and D.B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society. Series B (Methodological), vol. 39, no. 1, pp. 1-38, 1977.
3. Q. Zhu, B. Chen, N. Morgan, and A. Stolcke, "On using MLP features in LVCSR," in Interspeech. ISCA, 2004.
4. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," 2000, vol. 3, pp. 1635-1638 vol.3.
5. T. Minka, "Estimating a Dirichlet distribution," 2003.
6. P.J. Bickel and K.A. Doksum, Mathematical Statistics, vol. 1, Prentice Hall, 2007.
7. R. Sundberg, "Maximum likelihood theory for incomplete data from an exponential family," Scandinavian Journal of Statistics, vol. 1, no. 2, pp. 49-58, 1974.
8. A. Berger, "Convexity, maximum likelihood and all that," Unpublished paper available at http://www. cs. cmu. edu/aberger, 1998.
9. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," The Journal of the Acoustical Society of America, vol. 87, pp. 1738, 1990.
10. M.D. Richard and R.P. Lippmann, "Neural network classifiers estimate Bayesian a posteriori probabilities," Neural computation, vol. 3, no. 4, pp. 461-483, 1991.
11. "The ICSI Quicknet Software Package," Available at http: //www.icsi.berkeley.edu/Speech/qn.html.