Gauss mixture vector quantization
Author:
- 13 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1769-1772
Abstract
Gauss mixtures are a popular class of models in statistics and statistical signal processing because they can provide good fits to smooth densities, because they have a rich theory, and because they can be well estimated by existing algorithms such as the EM (expectation maximization) algorithm. We here extend an information theoretic extremal property for source coding from Gaussian sources to Gauss mixtures using high rate quantization theory and extend a method originally used for LPC (linear predictive coding) speech vector quantization to provide a Lloyd clustering approach to the design of Gauss mixture models. The theory provides formulas relating minimum discrimination information (MDI) for model selection and the mean squared error resulting when the MDI criterion is used in an optimized robust classified vector quantizer. It also provides motivation for the use of Gauss mixture models for robust compression systems for general random vectors.Keywords
This publication has 7 references indexed in Scilit:
- QuantizationIEEE Transactions on Information Theory, 1998
- Determinant Maximization with Linear Matrix Inequality ConstraintsSIAM Journal on Matrix Analysis and Applications, 1998
- On the role of mismatch in rate distortion theoryIEEE Transactions on Information Theory, 1997
- Multidimensional maximum-entropy covariance extensionIEEE Transactions on Information Theory, 1989
- Rate-distortion speech coding with a minimum discrimination information distortion measureIEEE Transactions on Information Theory, 1981
- Asymptotically optimal block quantizationIEEE Transactions on Information Theory, 1979
- Worst sources and robust codes for difference distortion measuresIEEE Transactions on Information Theory, 1975