Factored sparse inverse covariance matrices
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, II1009
- https://doi.org/10.1109/icassp.2000.859133
Abstract
Most HMM-based speech recognition systems use Gaussian mixtures as observation probability density functions. An important goal in all such systems is to improve parsimony. One method is to adjust the type of covariance matrices used. In this work, factored sparse inverse covariance matrices are introduced. Based on U'DU factorization, the inverse covariance matrix can be represented using linear regressive coefficients which 1) correspond to sparse patterns in the inverse covariance matrix (and therefore represent conditional independence properties of the Gaussian), and 2), result in a method of partial tying of the covariance matrices without requiring non-linear EM update equations. Results show that the performance of full-covariance Gaussians can be matched by factored sparse inverse covariance Gaussians having significantly fewer parameters.Keywords
This publication has 11 references indexed in Scilit:
- Linear predictive hidden Markov models and the speech signalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- PhoneBook: a phonetically-rich isolated-word telephone-speech databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Joint estimation of feature transformation parameters and Gaussian mixture model for speaker identificationSpeech Communication, 1999
- Semi-tied covariance matrices for hidden Markov modelsIEEE Transactions on Speech and Audio Processing, 1999
- Buried Markov models for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A review of large-vocabulary continuous-speechIEEE Signal Processing Magazine, 1996
- Sparse inverse covariance matrices and efficient maximum likelihood classification of hyperspectral dataInternational Journal of Remote Sensing, 1996
- The importance of cepstral parameter correlations in speech recognitionComputer Speech & Language, 1994
- Covariance SelectionAdvances in Applied Probability, 1978
- Covariance SelectionPublished by JSTOR ,1972