论文信息 - Maximum likelihood estimation for multivariate mixture observations of markov chains

Maximum likelihood estimation for multivariate mixture observations of markov chains

To use probabilistic functions of a Markov chain to model certain parameterizations of the speech signal, we extend an estimation technique of Liporace to the eases of multivariate mixtures, such as Gaussian sums, and products of mixtures. We also show how these problems relate to Liporace's original framework.

[1] L. Baum,et al. Growth transformations for functions on manifolds. , 1968 .

[2] L. Baum,et al. A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[3] H. Sorenson,et al. Recursive bayesian estimation using gaussian sums , 1971 .

[4] A. Gray,et al. Quantization and bit allocation in speech processing , 1976 .

[5] L. Rabiner,et al. On the effects of varying analysis parameters of an LPC based, isolated word recognizer , 1980 .

[6] J. G. Wilpon,et al. On the effects of varying analysis parameters on an LPC-based isolated word recognizer , 1981, The Bell System Technical Journal.

[7] Louis A. Liporace,et al. Maximum likelihood estimation for multivariate observations of Markov sources , 1982, IEEE Trans. Inf. Theory.

[8] L. R. Rabiner,et al. An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[9] A. Nádas. Hidden Markov chains, the forward-backward algorithm, and initial statistics , 1983 .