This presentation is intended to be a short course on inference and filtering in hidden Markov models (HMMs) and state space models. These models comprise a hidden (unobserved) Markov chain (either with discrete or continuous state space) that governs the distribution of an observed stochastic process. An example of a HMM is a regime-switching model for stock returns in which the stock return d...

In this paper, a new acoustic model called time-inhomogeneous hidden Bernoulli model (TI-HBM) is introduced as an alternative to hidden Markov model (HMM) in continuous speech recognition. Contrary to HMM, the state transition process in TI-HBM is not a Markov process, rather it is an independent (generalized Bernoulli) process. This difference leads to elimination of dynamic programming at sta...

Spelled letter recognition over the telephone line is essential for applications that involve names or addresses. In this paper we discuss the implementation and present results of a speaker independent spelled letter recognizer, trained and tested on the European project SPEECHDAT corpus. The system was implemented using HTK V2.0 (Hidden Markov Model Toolkit) software development tool and the ...

This paper presents an automatic face recognition system, which bases on two-dimensional hidden Markov models. The traditional HMM uses one-dimensional data vectors, which is a drawback in the case of 2D image processing, as part of the information is lost during the conversion. The article presents the full ergodic 2D-HMM and used it to identify faces. The experimental results demonstrate that...

Faced with the problem of characterizing systematic changes in multivariate time series in an unsupervised manner, we derive and test two methods of regularizing hidden Markov models for this task. Regularization on state transitions provides smooth transitioning among states, such that the sequences are split into broad, contiguous segments. Our methods are compared with a recent hierarchical ...

We present a Hidden Markov Model (HMM) for inferring the hidden psychological state (or neural activity) during single trial fMRI activation experiments with blocked task paradigms. Inference is based on Bayesian methodology, using a combination of analytical and a variety of Markov Chain Monte Carlo (MCMC) sampling techniques. The advantage of this method is that detection of short time learni...

A hidden Markov model (HMM) defines a joint probability distribution of a series of observations xt and hidden states zt for t = 1, . . . , T . We use x1:T and z1:T to refer to the full sequence of observations and states respectively. In a HMM the prior on the state sequence is assumed to satisfy the Markov property, which is to say that the probability of each state zt depends only on the pre...

This paper describes a hybrid system that applies maximum entropy (MaxEnt) model with Hidden Markov model (HMM) and some linguistic rules to recognize name entities in Oriya language. The main advantage of our system is, we are using both HMM and MaxEnt model successively with some manually developed linguistic rules. First we are using MaxEnt to identify name entities in Oria corpus, then tagg...

Recently, a trajectory model, derived from the hidden Markov model (HMM) by imposing explicit relationships between static and dynamic features, has been proposed. The derived model, named trajectory HMM, can alleviate two limitations of the HMM: constant statistics within a state and conditional independence assumption of state output probabilities. In the present paper, a speaker adaptation a...

In this paper we describe an embedded Hidden Markov Model (HMM)-based approach for face detection and recognition that uses an eecient set of observation vectors obtained from the 2D-DCT coeecients. The embedded HMM can model the two dimensional data better than the one-dimensional HMM and is computationally less complex than the two-dimensional HMM. This model is appropriate for face images si...