Showing papers on "Hidden Markov model published in 2002"

Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms

Abstract: We describe new algorithms for training tagging models, as an alternative to maximum-entropy models or conditional random fields (CRFs). The algorithms rely on Viterbi decoding of training examples, combined with simple additive updates. We describe theory justifying the algorithms through a modification of the proof of convergence of the perceptron algorithm for classification problems. We give experimental results on part-of-speech tagging and base noun phrase chunking, in both cases showing improvements over results for a maximum-entropy tagger.

Hidden Markov processes

Abstract: An overview of statistical and information-theoretic aspects of hidden Markov processes (HMPs) is presented. An HMP is a discrete-time finite-state homogeneous Markov chain observed through a discrete-time memoryless invariant channel. In recent years, the work of Baum and Petrie (1966) on finite-state finite-alphabet HMPs was expanded to HMPs with finite as well as continuous state spaces and a general alphabet. In particular, statistical properties and ergodic theorems for relative entropy densities of HMPs were developed. Consistency and asymptotic normality of the maximum-likelihood (ML) parameter estimator were proved under some mild conditions. Similar results were established for switching autoregressive processes. These processes generalize HMPs. New algorithms were developed for estimating the state, parameter, and order of an HMP, for universal coding and classification of HMPs, and for universal decoding of hidden Markov channels. These and other related topics are reviewed.

Named Entity Recognition using an HMM-based Chunk Tagger

Abstract: This paper proposes a Hidden Markov Model (HMM) and an HMM-based chunk tagger, from which a named entity (NE) recognition (NER) system is built to recognize and classify names, times and numerical quantities. Through the HMM, our system is able to apply and integrate four types of internal and external evidences: 1) simple deterministic internal feature of the words, such as capitalization and digitalization; 2) internal semantic feature of important triggers; 3) internal gazetteer feature; 4) external macro context feature. In this way, the NER problem can be resolved effectively. Evaluation of our system on MUC-6 and MUC-7 English NE tasks achieves F-measures of 96.6% and 94.1% respectively. It shows that the performance is significantly better than reported by any other machine-learning system. Moreover, the performance is even consistently better than those based on handcrafted rules.

Machine Learning for Sequential Data: A Review

Abstract: Statistical learning problems in many fields involve sequential data. This paper formalizes the principal learning tasks and describes the methods that have been developed within the machine learning research community for addressing these problems. These methods include sliding window methods, recurrent sliding windows, hidden Markov models, conditional random fields, and graph transformer networks. The paper also discusses some open research issues.

Bayesian Methods for Hidden Markov Models

Abstract: Markov chain Monte Carlo (MCMC) sampling strategies can be used to simulate hidden Markov model (HMM) parameters from their posterior distribution given observed data. Some MCMC methods used in practice (for computing likelihood, conditional probabilities of hidden states, and the most likely sequence of states) can be improved by incorporating established recursive algorithms. The most important of these is a set of forward-backward recursions calculating conditional distributions of the hidden states given observed data and model parameters. I show how to use the recursive algorithms in an MCMC context and demonstrate mathematical and empirical results showing a Gibbs sampler using the forward-backward recursions mixes more rapidly than another sampler often used for HMMs. Iintroduce an augmented variables technique for obtaining unique state labels in HMMs and finite mixture models. I show how recursive computing allows the statistically efficient use of MCMC output when estimating the hidden states. I...

Extraction of visual features for lipreading

Abstract: The multimodal nature of speech is often ignored in human-computer interaction, but lip deformations and other body motion, such as those of the head, convey additional information. We integrate speech cues from many sources and this improves intelligibility, especially when the acoustic signal is degraded. The paper shows how this additional, often complementary, visual speech information can be used for speech recognition. Three methods for parameterizing lip image sequences for recognition using hidden Markov models are compared. Two of these are top-down approaches that fit a model of the inner and outer lip contours and derive lipreading features from a principal component analysis of shape or shape and appearance, respectively. The third, bottom-up, method uses a nonlinear scale-space analysis to form features directly from the pixel intensity. All methods are compared on a multitalker visual speech recognition task of isolated letters.

An HMM model for coiled-coil domains and a comparison with PSSM-based predictions.

Abstract: Motivation: Large-scale sequence data require methods for the automated annotation of protein domains. Many of the predictive methods are based either on a Position Specific Scoring Matrix (PSSM) of fixed length or on a windowless Hidden Markov Model (HMM). The performance of the two approaches is tested for Coiled-Coil Domains (CCDs). The prediction of CCDs is used frequently, and its optimization seems worthwhile. Results: We have conceived MARCOIL, an HMM for the recognition of proteins with a CCD on a genomic scale. A cross-validated study suggests that MARCOIL improves predictions compared to the traditional PSSM algorithm, especially for some protein families and for short CCDs. The study was designed to reveal differences inherent in the two methods. Potential confounding factors such as differences in the dimension of parameter space and in the parameter values were avoided by using the same amino acid propensities and by keeping the transition probabilities of the HMM constant during cross-validation. Availability: The prediction program and the databases are available at http://www.wehi.edu.au/bioweb/Mauro/

Layered representations for human activity recognition

Abstract: We present the use of layered probabilistic representations using Hidden Markov Models for performing sensing, learning, and inference at multiple levels of temporal granularity. We describe the use of the representation in a system that diagnoses states of a user's activity based on real-time streams of evidence from video, acoustic, and computer interactions. We review the representation, present an implementation, and report on experiments with the layered representation in an office-awareness application.

Multiresolution Markov models for signal and image processing

Abstract: Reviews a significant component of the rich field of statistical multiresolution (MR) modeling and processing. These MR methods have found application and permeated the literature of a widely scattered set of disciplines, and one of our principal objectives is to present a single, coherent picture of this framework. A second goal is to describe how this topic fits into the even larger field of MR methods and concepts-in particular, making ties to topics such as wavelets and multigrid methods. A third goal is to provide several alternate viewpoints for this body of work, as the methods and concepts we describe intersect with a number of other fields. The principle focus of our presentation is the class of MR Markov processes defined on pyramidally organized trees. The attractiveness of these models stems from both the very efficient algorithms they admit and their expressive power and broad applicability. We show how a variety of methods and models relate to this framework including models for self-similar and 1/f processes. We also illustrate how these methods have been used in practice.

Dynamic Bayesian networks for audio-visual speech recognition

Abstract: The use of visual features in audio-visual speech recognition (AVSR) is justified by both the speech generation mechanism, which is essentially bimodal in audio and visual representation, and by the need for features that are invariant to acoustic noise perturbation. As a result, current AVSR systems demonstrate significant accuracy improvements in environments affected by acoustic noise. In this paper, we describe the use of two statistical models for audio-visual integration, the coupled HMM (CHMM) and the factorial HMM (FHMM), and compare the performance of these models with the existing models used in speaker dependent audio-visual isolated word recognition. The statistical properties of both the CHMM and FHMM allow to model the state asynchrony of the audio and visual observation sequences while preserving their natural correlation over time. In our experiments, the CHMM performs best overall, outperforming all the existing models and the FHMM.

A joint inter- and intrascale statistical model for Bayesian wavelet based image denoising

Abstract: This paper presents a new wavelet-based image denoising method, which extends a "geometrical" Bayesian framework. The new method combines three criteria for distinguishing supposedly useful coefficients from noise: coefficient magnitudes, their evolution across scales and spatial clustering of large coefficients near image edges. These three criteria are combined in a Bayesian framework. The spatial clustering properties are expressed in a prior model. The statistical properties concerning coefficient magnitudes and their evolution across scales are expressed in a joint conditional model. The three main novelties with respect to related approaches are (1) the interscale-ratios of wavelet coefficients are statistically characterized and different local criteria for distinguishing useful coefficients from noise are evaluated, (2) a joint conditional model is introduced, and (3) a novel anisotropic Markov random field prior model is proposed. The results demonstrate an improved denoising performance over related earlier techniques.

Policy recognition in the abstract hidden Markov model

Abstract: In this paper, we present a method for recognising an agent's behaviour in dynamic, noisy, uncertain domains, and across multiple levels of abstraction. We term this problem on-line plan recognition under uncertainty and view it generally as probabilistic inference on the stochastic process representing the execution of the agent's plan. Our contributions in this paper are twofold. In terms of probabilistic inference, we introduce the Abstract Hidden Markov Model (AHMM), a novel type of stochastic processes, provide its dynamic Bayesian network (DBN) structure and analyse the properties of this network. We then describe an application of the Rao-Blackwellised Particle Filter to the AHMM which allows us to construct an efficient, hybrid inference method for this model. In terms of plan recognition, we propose a novel plan recognition framework based on the AHMM as the plan execution model. The Rao-Blackwellised hybrid inference for AHMM can take advantage of the independence properties inherent in a model of plan execution, leading to an algorithm for online probabilistic plan recognition that scales well with the number of levels in the plan hierarchy. This illustrates that while stochastic models for plan execution can be complex, they exhibit special structures which, if exploited, can lead to efficient plan recognition algorithms. We demonstrate the usefulness of the AHMM framework via a behaviour recognition system in a complex spatial environment using distributed video surveillance data.

Algorithms for optimal scheduling and management of hidden Markov model sensors

Abstract: The author considers a hidden Markov model (HMM) where a single Markov chain is observed by a number of noisy sensors. Due to computational or communication constraints, at each time instant, one can select only one of the noisy sensors. The sensor scheduling problem involves designing algorithms for choosing dynamically at each time instant which sensor to select to provide the next measurement. Each measurement has an associated measurement cost. The problem is to select an optimal measurement scheduling policy to minimize a cost function of estimation errors and measurement costs. The optimal measurement policy is solved via stochastic dynamic programming. Sensor management issues and suboptimal scheduling algorithms are also presented. A numerical example that deals with the aircraft identification problem is presented.

Multi-Space Probability Distribution HMM

Abstract: This paper proposes a new kind of hidden Markov model (HMM) based on multi-space probability distribution, and derives a parameter estimation algorithm for the extended HMM HMMs are widely used statistical models for characterizing sequences of speech spectra, and have been successfully applied to speech recognition systems HMMs are categorized into discrete HMMs and continuous HMMs, which can model sequences of discrete symbols and continuous vectors, respectively However, we cannot apply both the conventional discrete and continuous HMMs to observation sequences which consist of continuous values and discrete symbols: F0 pattern modeling of speech is a good illustration The proposed HMM includes discrete HMM and continuous HMM as special cases, and furthermore, can model sequences which consist of observation vectors with variable dimensionality and discrete symbols key words: hidden Markov model, text-to-speech, F0, multispace probability distribution

Structure analysis of soccer video with hidden Markov models

Abstract: In this paper, we present algorithms for parsing the structure of produced soccer programs. The problem is important in the context of a personalized video streaming and browsing system. While prior work focuses on the detection of special events such as goals or corner kicks, this paper is concerned with generic structural elements of the game. We begin by defining two mutually exclusive states of the game, play and break based on the rules of soccer. We select a domain-tuned feature set, dominant color ratio and motion intensity, based on the special syntax and content characteristics of soccer videos. Each state of the game has a stochastic structure that is modeled with a set of hidden Markov models. Finally, standard dynamic programming techniques are used to obtain the maximum likelihood segmentation of the game into the two states. The system works well, with 83.5% classification accuracy and good boundary timing from extensive tests over diverse data sets.

Fitting Gaussian Markov Random Fields to Gaussian Fields

Abstract: This paper discusses the following task often encountered in building Bayesian spatial models: construct a homogeneous Gaussian Markov random field (GMRF) on a lattice with correlation properties either as present in some observed data, or consistent with prior knowledge. The Markov property is essential in designing computationally efficient Markov chain Monte Carlo algorithms to analyse such models. We argue that we can restate both tasks as that of fitting a GMRF to a prescribed stationary Gaussian field on a lattice when both local and global properties are important. We demonstrate that using the Kullback-Leibler discrepancy often fails for this task, giving severely undesirable behaviour of the correlation function for lags outside the neighbourhood. We propose a new criterion that resolves this difficulty, and demonstrate that GMRFs with small neighbourhoods can approximate Gaussian fields surprisingly well even with long correlation lengths. Finally, we discuss implications of our findings for likelihood based inference for general Markov random fields when global properties are also important.

A memory-efficient dynamic programming algorithm for optimal alignment of a sequence to an RNA secondary structure.

Abstract: Covariance models (CMs) are probabilistic models of RNA secondary structure, analogous to profile hidden Markov models of linear sequence. The dynamic programming algorithm for aligning a CM to an RNA sequence of length N is O(N3) in memory. This is only practical for small RNAs. I describe a divide and conquer variant of the alignment algorithm that is analogous to memory-efficient Myers/Miller dynamic programming algorithms for linear sequence alignment. The new algorithm has an O(N2 log N) memory complexity, at the expense of a small constant factor in time. Optimal ribosomal RNA structural alignments that previously required up to 150 GB of memory now require less than 270 MB.

A coupled HMM for audio-visual speech recognition

Abstract: In recent years several speech recognition systems that use visual together with audio information showed significant increase in performance over the standard speech recognition systems. The use of visual features is justified by both the bimodality of the speech generation and by the need of features that are invariant to acoustic noise perturbation. The audio-visual speech recognition system presented in this paper introduces a novel audio-visual fusion technique that uses a coupled hidden Markov model (HMM). The statistical properties of the coupled-HMM allow us to model the state asynchrony of the audio and visual observations sequences while still preserving their natural correlation over time. The experimental results show that the coupled HMM outperforms the multistream HMM in audio visual speech recognition.

Rotation invariant texture characterization and retrieval using steerable wavelet-domain hidden Markov models

Abstract: We present a statistical model for characterizing texture images based on wavelet-domain hidden Markov models. With a small number of parameters, the new model captures both the subband marginal distributions and the dependencies across scales and orientations of the wavelet descriptors. Applied to the steerable pyramid, once it is trained for an input texture image, the model can be easily steered to characterize that texture at any other orientation. Furthermore, after a diagonalization operation, we obtain a rotation-invariant model of the texture image. We also propose a fast algorithm to approximate the Kullback-Leibler distance between two wavelet-domain hidden Markov models. We demonstrate the effectiveness of the new texture models in retrieval experiments with large image databases, where significant improvements are shown.

Gait-based recognition of humans using continuous HMMs

Abstract: Gait is a spatio-temporal phenomenon that typifies the motion characteristics of an individual. In this paper, we propose a view-based approach to recognize humans through gait. The width of the outer contour of the binarized silhouette of a walking person is chosen as the image feature. A set of stances or key frames that occur during the walk cycle of an individual is chosen. Euclidean distances of a given image from this stance set are computed and a lower-dimensional observation vector is generated. A continuous hidden Markov model (HMM) is trained using several such lower-dimensional vector sequences extracted from the video. This methodology serves to compactly capture structural and transitional features that are unique to an individual. The statistical nature of the HMM renders overall robustness to gait representation and recognition. The human identification performance of the proposed scheme is found to be quite good when tested in natural walking conditions.

Mode Estimation of Probabilistic Hybrid Systems

Abstract: Model-based diagnosis and mode estimation capabilities excel at diagnosing systems whose symptoms are clearly distinguished from normal behavior A strength of mode estimation, in particular, is its ability to track a system's discrete dynamics as it moves between different behavioral modes However, often failures bury their symptoms amongst the signal noise, until their effects become catastrophicWe introduce a hybrid mode estimation system that extracts mode estimates from subtle symptoms First, we introduce a modeling formalism, called concurrent probabilistic hybrid automata (cPHA), that merge hidden Markov models (HMM) with continuous dynamical system models Second, we introduce hybrid estimation as a method for tracking and diagnosing cPHA, by unifying traditional continuous state observers with HMM belief update Finally, we introduce a novel, any-time, any-space algorithm for computing approximate hybrid estimates

Optical character recognition for cursive handwriting

Abstract: A new analytic scheme, which uses a sequence of image segmentation and recognition algorithms, is proposed for the off-line cursive handwriting recognition problem. First, some global parameters, such as slant angle, baselines, stroke width and height, are estimated. Second, a segmentation method finds character segmentation paths by combining gray-scale and binary information. Third, a hidden Markov model (HMM) is employed for shape recognition to label and rank the character candidates. For this purpose, a string of codes is extracted from each segment to represent the character candidates. The estimation of feature space parameters is embedded in the HMM training stage together with the estimation of the HMM model parameters. Finally, information from a lexicon and from the HMM ranks is combined in a graph optimization problem for word-level recognition. This method corrects most of the errors produced by the segmentation and HMM ranking stages by maximizing an information measure in an efficient graph search algorithm. The experiments indicate higher recognition rates compared to the available methods reported in the literature.

Toward Automatic Music Audio Summary Generation from Signal Analysis.

Abstract: This paper deals with the automatic generation of music audio summaries from signal analysis without the use of any other information. The strategy employed here is to consider the audio signal as a succession of “states” (at various scales) corresponding to the structure (at various scales) of a piece of music. This is, of course, only applicable to certain kinds of musical genres based on some kind of repetition. From the audio signal, we first derive dynamic features representing the time evolution of the energy content in various frequency bands. These features constitute our observations from which we derive a representation of the music in terms of “states”. Since human segmentation and grouping performs better upon subsequent hearings, this “natural” approach is followed here. The first pass of the proposed algorithm uses segmentation in order to create “templates”. The second pass uses these templates in order to propose a structure of the music using unsupervised learning methods (Kmeans and hidden Markov model). The audio summary is finally constructed by choosing a representative example of each state. Further refinements of the summary audio signal construction, uses overlapadd, and a tempo detection/ beat alignment in order to improve the audio quality of the created summary.

A comparison of profile hidden Markov model procedures for remote homology detection.

Abstract: Profile hidden Markov models (HMMs) are amongst the most successful procedures for detecting remote homology between proteins. There are two popular profile HMM programs, HMMER and SAM. Little is known about their performance relative to each other and to the recently improved version of PSI-BLAST. Here we compare the two programs to each other and to non-HMM methods, to determine their relative performance and the features that are important for their success. The quality of the multiple sequence alignments used to build models was the most important factor affecting the overall performance of profile HMMs. The SAM T99 procedure is needed to produce high quality alignments automatically, and the lack of an equivalent component in HMMER makes it less complete as a package. Using the default options and parameters as would be expected of an inexpert user, it was found that from identical alignments SAM consistently produces better models than HMMER and that the relative performance of the model-scoring components varies. On average, HMMER was found to be between one and three times faster than SAM when searching databases larger than 2000 sequences, SAM being faster on smaller ones. Both methods were shown to have effective low complexity and repeat sequence masking using their null models, and the accuracy of their E-values was comparable. It was found that the SAM T99 iterative database search procedure performs better than the most recent version of PSI-BLAST, but that scoring of PSI-BLAST profiles is more than 30 times faster than scoring of SAM models.

Combining pairwise sequence similarity and support vector machines for remote protein homology detection

Abstract: One key element in understanding the molecular machinery of the cell is to understand the meaning, or function, of each protein encoded in the genome. A very successful means of inferring the function of a previously unannotated protein is via sequence similarity with one or more proteins whose functions are already known. Currently, one of the most powerful such homology detection methods is the SVM-Fisher method of Jaakkola, Diekhans and Haussler (ISMB 2000). This method combines a generative, profile hidden Markov model (HMM) with a discriminative classification algorithm known as a support vector machine (SVM). The current work presents an alternative method for SVM-based protein classification. The method, SVM-pairwise, uses a pairwise sequence similarity algorithm such as Smith-Waterman in place of the HMM in the SVM-Fisher method. The resulting algorithm, when tested on its ability to recognize previously unseen families from the SCOP database, yields significantly better remote protein homology detection than SVM-Fisher, profile HMMs and PSI-BLAST.

Extract highlights from baseball game video with hidden Markov models

Abstract: We describe a statistical method to detect highlights in a baseball game video. The input video is first segmented into scene shots, within which the camera motion is continuous. Our approach is based on the observations that (1) most highlights in baseball games are composed of certain types of scene shots and (2) those scene shots exhibit special transition context in time. To exploit those two observations, we first build statistical models for each type of scene shots with products of histograms, and then for each type of highlight a hidden Markov model is learned to represent the context of transition in the time domain. A probabilistic model can be obtained by combining the two, which is used for highlight detection and classification. Satisfactory results have been achieved on initial experimental results.

Soccer highlights detection and recognition using HMMs

Abstract: In this paper we report on our experience in the detection and recognition of soccer highlights in videos using hidden Markov models. A first approach relies on camera motion only, whereas a second one also includes information regarding the location of players on the playing field. While the former approach requires less information, the latter has proven to be more precise. Our experimental evaluation yields interesting results.