Hidden Markov Model Method Research Articles

Dynamic Grasp Recognition Using Time Clustering, Gaussian Mixture Models and Hidden Markov Models

The human hand has the capability of fulfilling various everyday-life tasks using the combination of biological mechanisms, sensors and controls. Autonomously controlling multifingered robots is a challenge, which holds the key to related multidisciplinary research and a wide spectrum of applications in intelligent robotics. We demonstrate the state of the art in recognizing continuous grasping gestures of human hands in this paper. We propose a novel time clustering method (TC) and modified Gaussian mixture models (GMMs) and compare them with hidden Markov models (HMMs). The TC outperforms the GMM and HMM methods in terms of recognition rate and potentially in computational cost. Future work is focused on real-time recognition and grasp qualitative description.

Prediction of regulatory elements in mammalian genomes using chromatin signatures

BackgroundRecent genomic scale survey of epigenetic states in the mammalian genomes has shown that promoters and enhancers are correlated with distinct chromatin signatures, providing a pragmatic way for systematic mapping of these regulatory elements in the genome. With rapid accumulation of chromatin modification profiles in the genome of various organisms and cell types, this chromatin based approach promises to uncover many new regulatory elements, but computational methods to effectively extract information from these datasets are still limited.ResultsWe present here a supervised learning method to predict promoters and enhancers based on their unique chromatin modification signatures. We trained Hidden Markov models (HMMs) on the histone modification data for known promoters and enhancers, and then used the trained HMMs to identify promoter or enhancer like sequences in the human genome. Using a simulated annealing (SA) procedure, we searched for the most informative combination and the optimal window size of histone marks.ConclusionCompared with the previous methods, the HMM method can capture the complex patterns of histone modifications particularly from the weak signals. Cross validation and scanning the ENCODE regions showed that our method outperforms the previous profile-based method in mapping promoters and enhancers. We also showed that including more histone marks can further boost the performance of our method. This observation suggests that the HMM is robust and is capable of integrating information from multiple histone marks. To further demonstrate the usefulness of our method, we applied it to analyzing genome wide ChIP-Seq data in three mouse cell lines and correctly predicted active and inactive promoters with positive predictive values of more than 80%. The software is available at .

Automatic Recognition of Pathological Phoneme Production

Objective: Proper diagnosis and therapy of pathological pronunciation of phonemes play an important role in modern logopedics. To enhance the efficiency of diagnosis and therapy an automatic recognition of pathological phoneme pronunciation is addressed in this paper. The authors focus on the therapy of phoneme substitution disorders. Patients and Methods: Recognized speech samples come from speech-impaired Polish children and partially from persons imitating speech disorders. Recognized speech disorders were substitutions in pairs {s, ʂ}, {ɕ, ʂ}, {ʦ, tʂ+}, {ʨ, tʂ+}, {ʣ, dʐ+ }, and {ʥ, dʐ+ } embedded in Polish carrier words. In order to detect substitutions in the recognized words, recently proposed human factor cepstral coefficients (HFCC) have been implemented. Efficiency of the HFCC approach was compared to the application of standard mel-frequency cepstral coefficients (MFCC) as a feature vector. Both dynamic time warping (DTW), working on whole words or embedded phoneme patterns, and hidden Markov models (HMM) were used as classifiers. The HMM classifier was based on whole-word models as well as phoneme models. Results present a comparative analysis of DTW and HMM methods. Conclusions: The superiority of HFCC features over those of MFCC was demonstrated. Results obtained by DTW methods, mainly by modified phoneme-based DTW classifier, were slightly better in comparison with the HMM classifier. Results obtained for the detection of substitution in pairs {s, ʂ}, {ʦ, tʂ+}, {ʣ, ʣ+ } are very promising. The methods developed for these cases can be integrated into computer systems for speech therapy. For substitutions in pairs {ɕ, ʂ}, {ʨ, tʂ+}, {ʥ, dʐ+ } further research is necessary.

Speech separation using speaker-adapted eigenvoice speech models

We present a system for model-based source separation for use on single channel speech mixtures where the precise source characteristics are not known a priori. The sources are modeled using hidden Markov models (HMM) and separated using factorial HMM methods. Without prior speaker models for the sources in the mixture it is difficult to exactly resolve the individual sources because there is no way to determine which state corresponds to which source at any point in time. This is solved to a small extent by the temporal constraints provided by the Markov models, but permutations between sources remains a significant problem. We overcome this by adapting the models to match the sources in the mixture. We do this by representing the space of speaker variation with a parametric signal model-based on the eigenvoice technique for rapid speaker adaptation. We present an algorithm to infer the characteristics of the sources present in a mixture, allowing for significantly improved separation performance over that obtained using unadapted source models. The algorithm is evaluated on the task defined in the 2006 Speech Separation Challenge [Cooke, M.P., Lee, T.-W., 2008. The 2006 Speech Separation Challenge. Computer Speech and Language] and compared with separation using source-dependent models. Although performance is not as good as with speaker-dependent models, we show that the system based on model adaptation is able to generalize better to held out speakers.

Discriminative tonal feature extraction method in mandarin speech recognition

To utilize the supra-segmental nature of Mandarin tones, this article proposes a feature extraction method for hidden markov model (HMM) based tone modeling. The method uses linear transforms to project F 0 (fundamental frequency) features of neighboring syllables as compensations, and adds them to the original F 0 features of the current syllable. The transforms are discriminatively trained by using an objective function termed as “minimum tone error”, which is a smooth approximation of tone recognition accuracy. Experiments show that the new tonal features achieve 3.82% tone recognition rate improvement, compared with the baseline, using maximum likelihood trained HMM on the normal F 0 features. Further experiments show that discriminative HMM training on the new features is 8.78% better than the baseline.

A Hidden Markov Model to estimate population mixture and allelic copy-numbers in cancers using Affymetrix SNP arrays.

BackgroundAffymetrix SNP arrays can interrogate thousands of SNPs at the same time. This allows us to look at the genomic content of cancer cells and to investigate the underlying events leading to cancer. Genomic copy-numbers are today routinely derived from SNP array data, but the proposed algorithms for this task most often disregard the genotype information available from germline cells in paired germline-tumour samples. Including this information may deepen our understanding of the "true" biological situation e.g. by enabling analysis of allele specific copy-numbers. Here we rely on matched germline-tumour samples and have developed a Hidden Markov Model (HMM) to estimate allelic copy-number changes in tumour cells. Further with this approach we are able to estimate the proportion of normal cells in the tumour (mixture proportion).ResultsWe show that our method is able to recover the underlying copy-number changes in simulated data sets with high accuracy (above 97.71%). Moreover, although the known copy-numbers could be well recovered in simulated cancer samples with more than 70% cancer cells (and less than 30% normal cells), we demonstrate that including the mixture proportion in the HMM increases the accuracy of the method. Finally, the method is tested on HapMap samples and on bladder and prostate cancer samples.ConclusionThe HMM method developed here uses the genotype calls of germline DNA and the allelic SNP intensities from the tumour DNA to estimate allelic copy-numbers (including changes) in the tumour. It differentiates between different events like uniparental disomy and allelic imbalances. Moreover, the HMM can estimate the mixture proportion, and thus inform about the purity of the tumour sample.

Hidden Markov Models for Radio Localization in Mixed LOS/NLOS Conditions

This paper deals with the problem of radio localization of moving terminals (MTs) for indoor applications with mixed line-of-sight/non-line-of-sight (LOS/NLOS) conditions. To reduce false localizations, a grid-based Bayesian approach is proposed to jointly track the sequence of the positions and the sight conditions of the MT. This method is based on the assumption that both the MT position and the sight condition are Markov chains whose state is hidden in the received signals [hidden Markov model (HMM)]. The observations used for the HMM localization are obtained from the power-delay profile of the received signals. In ultrawideband (UWB) systems, the use of the whole power-delay profile, rather than the total power only, allows to reach higher localization accuracy, as the power-profile is a joint measurement of time of arrival and power. Numerical results show that the proposed HMM method improves the accuracy of localization with respect to conventional ranging methods, especially in mixed LOS/NLOS indoor environments

VGIchan: Prediction and Classification of Voltage-Gated Ion Channels

This study describes methods for predicting and classifying voltage-gated ion channels. Firstly, a standard support vector machine (SVM) method was developed for predicting ion channels by using amino acid composition and dipeptide composition, with an accuracy of 82.89% and 85.56%, respectively. The accuracy of this SVM method was improved from 85.56% to 89.11% when combined with PSI-BLAST similarity search. Then we developed an SVM method for classifying ion channels (potassium, sodium, calcium, and chloride) by using dipeptide composition and achieved an overall accuracy of 96.89%. We further achieved a classification accuracy of 97.78% by using a hybrid method that combines dipeptide-based SVM and hidden Markov model methods. A web server VGIchan has been developed for predicting and classifying voltage-gated ion channels using the above approaches. VGIchan is freely available at www.imtech.res.in/raghava/vgichan/.

SVM-BASED PHONEME CLASSIFICATION AND LIP SHAPE REFINEMENT IN REAL-TIME LIP-SYNCH SYSTEM

In this paper, we present a real time lip-synch system that activates 2-D avatar's lip motion in synch with incoming speech utterance. To achieve the real time operation of the system, the processing time was minimized by "merge and split" procedures resulting in coarse-to-fine phoneme classification. At each stage of phoneme classification, the support vector machine (SVM) method was applied to reduce the computational load while maintaining the desired accuracy. The coarse-to-fine phoneme classification, is accomplished via two_stages of feature extraction: in the first stage, each speech frame is acoustically analyzed for three classes of lip opening using Mel Frequency Cepstral Coefficients (MFCC) as a feature; in the second stage, each frame is further refined for detailed lip shape using formant information. The method was implemented in 2-D lip animation and it was demonstrated that the system was effective in accomplishing real-time lip-synch. This approach was tested on a PC using the Microsoft Visual Studio with an Intel Pentium IV 1.4 Giga Hz CPU and 384 MB RAM. It was observed that the methods of phoneme merging and SVM achieved about twice the speed in recognition than the method employing the Hidden Markov Model (HMM). A typical latency time per a single frame observed using the proposed method was in the order of 18.22 milliseconds while an HMM method under identical conditions resulted about 30.67 milliseconds.

Profiling program behavior for anomaly intrusion detection based on the transition and frequency property of computer audit data

Intrusion detection is an important technique in the defense-in-depth network security framework. In recent years, it has been a widely studied topic in computer network security. In this paper, we present two methods, namely, the Hidden Markov Models (HMM) method and the Self Organizing Maps (SOM) method, to profile normal program behavior for anomaly intrusion detection based on computer audit data. The HMM method utilizes the transition property of events while SOM method relies on the frequency property of events. Two data sets, CERT synthetic Sendmail system call data collected in the University of New Mexico (UNM) and Live FTP system call data collected in the CNSIS lab of Xi'an Jiaotong University, were used to assess the two methods. Testing results show that the HMM method using the transition property of events produces good detection performance while high computational expense is required both for training and detection. The HMM method is better than other two methods reported previously in terms of detection accuracy for the same data set. The SOM method considering the frequency property of events, on the other hand, is suitable for real-time intrusion detection because of its capability of processing a large amount of data with low computational overhead.

Extraction of coherent relevant passages using hidden Markov models

In information retrieval, retrieving relevant passages, as opposed to whole documents, not only directly benefits the end user by filtering out the irrelevant information within a long relevant document, but also improves retrieval accuracy in general. A critical problem in passage retrieval is to extract coherent relevant passages accurately from a document, which we refer to as passage extraction . While much work has been done on passage retrieval, the passage extraction problem has not been seriously studied. Most existing work tends to rely on presegmenting documents into fixed-length passages which are unlikely optimal because the length of a relevant passage is presumably highly sensitive to both the query and document.In this article, we present a new method for accurately detecting coherent relevant passages of variable lengths using hidden Markov models (HMMs). The HMM-based method naturally captures the topical boundaries between passages relevant and nonrelevant to the query. Pseudo-feedback mechanisms can be naturally incorporated into such an HMM-based framework to improve parameter estimation. We show that with appropriate parameter estimation, the HMM method outperforms a number of strong baseline methods on two datasets. We further show how the HMM method can be applied on top of any basic passage extraction method to improve passage boundaries.

Normalized training for HMM-Based visual speech recognition

This paper discusses parameter estimation for a continuous density HMM (hidden Markov model) method of visual speech recognition. Past studies of visual speech recognition can be broadly divided into two approaches, the image-based method and the model-based method. The image-based method is a method in which some preprocessing, such as subsampling and principal component analysis, is applied to the pixel values of the original image, and the result is used as the feature vector. In this approach, the position and size of the lips and the illumination conditions have a direct effect on the recognition rate. Thus, the normalization of these factors is the basic technique. The ordinary approach in the conventional normalization is to provide a criterion independently of the HMM, and to apply normalization before learning. In this paper, normalization by the ML (maximum likelihood) criterion is considered. Normalized training is proposed in which the normalization processes for elements such as the position, size, inclination, mean brightness, and contrast of the lips are integrated with the training of the model. The proposed method is formulated on the basis of an EM (expectation maximization) algorithm in which monotonically increasing behavior of the likelihood of the training data is guaranteed, by iteration of normalized training. The effectiveness of the proposed method is demonstrated in a word recognition experiment using the M2VTS database. © 2006 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 89(11): 40–50, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.20281

Prediction of HLA-A2 binding peptides using Bayesian network.

Prediction of peptides binding to HLA (human leukocyte antigen) finds application in peptide vaccine design. A number of statistical and structural models have been developed in recent years for HLA binding peptide prediction. However, a Bayesian Network (BNT) model is not available. In this study we describe a BNT model for HLA-A2 binding peptide prediction. It has been demonstrated that the BNT model allows up to 99 % accurate identification of the HLA-A2 binding peptides and provides similar prediction accuracy compared to HMM (Hidden Markov Model) and ANN (Artificial Neural Network). At the same time, it has been shown that the BNT has that advantage that it allows more accurate performance for smaller sets of empirical data compared to the HMM and the ANN methods. When the size of the training set has been reduced to 40% from the original data, the identification of the HLA-A2 binding peptides by the BNT, ANN and HMM methods produced ARoc (area under receiver operating characteristic) values 0.88, 0.85, 0.85 respectively. The results of the work demonstrate certain advantages of using the Bayesian Networks in predicting the HLA binding peptides using smaller datasets.

Automatic music classification and summarization

Automatic music classification and summarization are very useful to music indexing, content-based music retrieval and on-line music distribution, but it is a challenge to extract the most common and salient themes from unstructured raw music data. In this paper, we propose effective algorithms to automatically classify and summarize music content. Support vector machines are applied to classify music into pure music and vocal music by learning from training data. For pure music and vocal music, a number of features are extracted to characterize the music content, respectively. Based on calculated features, a clustering algorithm is applied to structure the music content. Finally, a music summary is created based on the clustering results and domain knowledge related to pure and vocal music. Support vector machine learning shows a better performance in music classification than traditional Euclidean distance methods and hidden Markov model methods. Listening tests are conducted to evaluate the quality of summarization. The experiments on different genres of pure and vocal music illustrate the results of summarization are significant and effective.

Audio/visual mapping with cross-modal hidden Markov models

The audio/visual mapping problem of speech-driven facial animation has intrigued researchers for years. Recent research efforts have demonstrated that hidden Markov model (HMM) techniques, which have been applied successfully to the problem of speech recognition, could achieve a similar level of success in audio/visual mapping problems. A number of HMM-based methods have been proposed and shown to be effective by the respective designers, but it is yet unclear how these techniques compare to each other on a common test bed. In this paper, we quantitatively compare three recently proposed cross-modal HMM methods, namely the remapping HMM (R-HMM), the least-mean-squared HMM (LMS-HMM), and HMM inversion (HMMI). The objective of our comparison is not only to highlight the merits and demerits of different mapping designs, but also to study the optimality of the acoustic representation and HMM structure for the purpose of speech-driven facial animation. This paper presents a brief overview of these models, followed by an analysis of their mapping capabilities on a synthetic dataset. An empirical comparison on an experimental audio-visual dataset consisting of 75 TIMIT sentences is finally presented. Our results show that HMMI provides the best performance, both on synthetic and experimental audio-visual data.

Face recognition based on multi-class mapping of Fisher scores

A new hidden Markov model (HMM) based feature generation scheme is proposed for face recognition (FR) in this paper. In this scheme, HMM method is used to model classes of face images. A set of Fisher scores is calculated through partial derivative analysis of the parameters estimated in each HMM. These Fisher scores are further combined with some traditional features such as log-likelihood and appearance based features to form feature vectors that exploit the strengths of both local and holistic features of human face. Linear discriminant analysis (LDA) is then applied to analyze these feature vectors for FR. Performance improvements are observed over stand-alone HMM method and Fisher face method which uses appearance based feature vectors. A further study reveals that, by reducing the number of models involved in the training and testing stages of LDA, the proposed feature generation scheme can maintain very high discriminative power at much lower computational complexity comparing to the traditional HMM based FR system. Experimental results on a public available face database are provided to demonstrate the viability of this scheme.

BSS-HMM3s: An improved HMM method for identifying transcription factor binding sites

Today, an important problem in molecular biology is the study of gene expression mechanism. The first step in determining differential gene expression is the binding of sequence specific transcription factors to regulatory regions of the genes. An important aspect to understand how a given transcription factor functions is to know the entire gamut of binding sites and potential target genes that the factor may regulate. In this paper, we presented an improved prediction method based on hidden Markov model (HMM) called BSS-HMM(3)s (binding site search based on third-order HMMs) for transcription factor binding sites. The results show that the predicted sensitivity and specificity of BSS-HMM(3)s increased 11.95 and 12.97%, respectively, compared with Match.

Best alpha-helical transmembrane protein topology predictions are achieved using hidden Markov models and evolutionary information.

Methods that predict the topology of helical membrane proteins are standard tools when analyzing any proteome. Therefore, it is important to improve the performance of such methods. Here we introduce a novel method, PRODIV-TMHMM, which is a profile-based hidden Markov model (HMM) that also incorporates the best features of earlier HMM methods. In our tests, PRODIV-TMHMM outperforms earlier methods both when evaluated on "low-resolution" topology data and on high-resolution 3D structures. The results presented here indicate that the topology could be correctly predicted for approximately two-thirds of all membrane proteins using PRODIV-TMHMM. The importance of evolutionary information for topology prediction is emphasized by the fact that compared with using single sequences, the performance of PRODIV-TMHMM (as well as two other methods) is increased by approximately 10 percentage units by the use of homologous sequences. On a more general level, we also show that HMM-based (or similar) methods perform superiorly to methods that focus mainly on identification of the membrane regions.

Constrained Optimization for Audio-to-Visual Conversion

We have developed a new audio-to-visual conversion algorithm that uses a constrained optimization approach to take advantage of dynamics of mouth movements. Based on facial muscle analysis, the dynamics of mouth movements is modeled, and constraints are obtained from it. The obtained constraints are used to estimate visual parameters from speech in a framework of hidden Markov model (HMM)-based visual parameter estimation. To solve the constrained optimization problem, the Lagrangian approach is used to transform the constrained problem into an unconstrained problem in our implementation. The proposed method is tested on various noisy environments to show its robustness and correctness. Our proposed algorithm is favorably compared with the mixture-based HMM method, which also uses audio-visual HMMs and finds optimal estimates based on a joint audio-visual probability distribution. Our proposed algorithm can estimate optimal visual parameters while satisfying the constraints and avoiding performance degradation in noisy environments.

Self-adaptive design of hidden Markov models

Hidden Markov models (HMMs) are stochastic models widely used in speech and image processing in recent years. The number of states in a classical HMMs is usually predefined and fixed during training, and may be quite different from the real number of hidden states of the signal source. Moreover, in pattern recognition applications, different signal sources probably have different state numbers, thereby cannot be well modeled by HMMs with a fixed state number. This paper proposes a self-adaptive design method of HMMs to overcome this limitation. According to this design, an HMM automatically matches its state number to the real state number of the signal source being modeled. To realize a practicable training algorithm for the new HMM, this paper first introduces an entropic definition of the a priori probability of the model and accordingly a maximum a posteriori (MAP) training strategy, and then designs an MAP training algorithm in the case of fixed state number based on the deterministic annealing (DA) technique. Based on this MAP training, a complete training method named shrink algorithm is finally proposed for the new HMM. Experimental results indicate that self-adaptive HMMs can model stochastic signals more accurately and have better performance in pattern recognition than classical models.