Maximum likelihood estimation for general hidden semi-Markov processes with backward recurrence time dependence
نویسندگان
چکیده
This article concerns the study of the asymptotic properties of the maximum likelihood estimator (MLE) for the general hidden semi-Markov model (HSMM) with backward recurrence time dependence. By transforming the general HSMM into a general hidden Markov model, we prove that under some regularity conditions, the MLE is strongly consistent and asymptotically normal. We also provide useful expressions for the asymptotic covariance matrices, involving the MLE of the conditional sojourn times and the embedded Markov chain of the hidden semi-Markov chain.
منابع مشابه
Estimation of Hidden Markov Models with Nonparametric Simulated Maximum Likelihood
We propose a nonparametric simulated maximum likelihood estimation (NPSMLE) with built-in nonlinear ltering. By recursively approximating the unknown conditional densities, our method enables a maximum likelihood estimation of general dynamic models with latent variables including time-inhomogeneous and non-stationary processes. We establish the asymptotic properties of the NPSMLEs for hidden...
متن کاملQuasi-Newton method for maximum likelihood estimation of hidden Markov models
Hidden Markov models (HMMs) are used in many signal processing applications including speech recognition, blind equalization of digital communications channels, etc. The most widely used method for maximum likelihood estimation of HMM parameters is the forward-backward (or BaumWelch) algorithm which is an early example of application of the Expectation-Maximization (EM) principle. In this contr...
متن کاملSELECTIVE TRAINING FOR HIDDEN MARKOVMODELS with APPLICATIONS to SPEECHCLASSIFICATIONbyLevent
Traditional maximum likelihood estimation of hidden Markov model parameters aims at maximizing the overall probability across the training tokens of a given speech unit. Therefore, it disregards any interaction and biases across the models in the training procedure. Often the resulting model parameters do not result in minimum error classiication in the training set. A new selective training me...
متن کاملMaximum A Posteriori Path Estimation with Input Trace Perturbation: Algorithms and Application to Credible Rating of Human Routines
Rating how well a routine activity is performed can be valuable in a variety of domains. Making the rating inexpensive and credible is a key aspect of the problem. We formalize the problem as MAP estimation in HMMs where the incoming trace needs repair. We present polynomial time algorithms for computing minimal repairs with maximal likelihood for HMMs, Hidden Semi-Markov Models (HSMMs) and a f...
متن کاملMarkov process applied to degradation modelling
.................................................................................................................... 2 Preface ....................................................................................................................... 3 Acknowledgements................................................................................................... 4 Chapter 1: Introduction .........
متن کامل