Refactoring acoustic models using variational density approximation

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

Volumn , Issue , 2009, Pages 4473-4476

  Dognin, Pierre L ^a   Hershey, John R ^a   Goel, Vaibhava ^a   Olsen, Peder A ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Acoustic model clustering; Bhattacharyya divergence; KL divergence; Variational approximations

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODEL CLUSTERING; APRIORI; BHATTACHARYYA DIVERGENCE; COMPLEX MODEL; DENSITY APPROXIMATIONS; ERROR RATE; EXPECTATION-MAXIMIZATION ALGORITHMS; GAUSSIAN MIXTURE MODEL; GAUSSIANS; KL DIVERGENCE; LOWER COMPLEXITY; MODEL SIZE; MODEL-BASED; REFACTORINGS; REFERENCE MODELS; TARGET SIZE; TRAINING DATA; VARIATIONAL APPROXIMATIONS;

ACOUSTICS; BLIND SOURCE SEPARATION; IMAGE SEGMENTATION; MAGNETOSTRICTIVE DEVICES; SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 70349225968     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4960623     Document Type: Conference Paper

References (10)

1. S. Kullback, Information Theory and Statistics, Dover Publications, Mileona, New York, 1997.
2. A. Bhattacharyya, "On a measure of divergence between two statistical populations defined by probability distributions," Bull. Calcutta Math. Soc., vol. 35, pp. 99-109, 1943.
3. Keinosuke Fukunaga, Statistical Pattern Recognition, Academic Press, Inc., San Diego, CA, 1990.
4. John Hershey and Peder Olsen, "Approximating the Kullback Leibler divergence between gaussian mixture models," in ICASSP, Honolulu, Hawaii, April 2007.
5. Peder Olsen and John Hershey, "Bhattacharyya error and divergence using variational importance sampling," in ICSLP, Antwerp, Belgium, August 2007.
6. Jacob Goldberger and Sam Roweis, "Hierarchical clustering of a mixture model," in Advances in Neural Information Processing Systems 17, Lawrence K. Saul, Yair Weiss, and Léon Bottou, Eds., pp. 505-512. MIT Press, Cambridge, MA, 2005.
7. Raimo Bakis, David Nahamoo, Michael A. Picheny, and Jan Sedivy, "Hierarchical labeler in a speech recognition system," U.S. Patent 6023673. filed June 4, 1997, and issued February 8, 2000.
8. Kai Zhang and James T. Kwok, "Simplifying mixture models through function approximation," in Advances in Neural Information Processing Systems 19, B. Schölkopf, J. Platt, and T. Hoffman, Eds., pp. 1577-1584. MIT Press, Cambridge,MA, 2007.
9. Xiao-Bing Li, Frank K. Soong, Tor André Myrvoll, and Ren-Hua Wang, "Optimal Clustering and Non-Uniform Allocation of Gaussian Kernels in Scalar Dimension for HMM Compression," in ICASSP, 2005, vol. 1, pp. 669-672.
10. Sabine Deligne, Ellen Eide, Ramesh Gopinath, Dimitry Kanefsky, Benoit Maison, Peder Olsen, Harry Printz, and Jan Sedivy, "Low-resource speech recognition of 500-word vocabularies," in Eurospeech, 2001.