Using Hidden Markov Models for ECG Characterisation

This paper proposes an approach combining the set of Krawtchouk moments and HMMs (Hidden Markov Models) for unconstrained offline handwritten Chinese character recognition. The Krawtchouk moments can be effectively used as pattern features in analysis of two-dimensional images. Since the basis set is orthogonal in the discrete domain of the image coordinate space, the implementation of Krawtchouk moments doesn't involve any numerical approximation or coordinate transformation. This property makes Krawtchouk moments superior to conventional, more continuous moments such as Legendre moments and Zernike moments. In the field of character recognition, HMMs architecture has been used widely because of its strong adaptability to written distortion and variability. In this paper, Krawtchouk moments and HMMs are combined to recognize unconstrained offline handwritten Chinese amount in words. Experiments show that the average recognition of Krawtchouk is higher than Zernike and Legendre moments within the HMM framework.

A defining characteristic of intelligent tutoring systems is their ability to adapt the learning plan to individual variances of the learners. A main question in this adaptation is the order of the learning concepts an intelligent tutoring system should offer to a human learner, when there is a dependency relationship between the concepts. We studied this problem by utilizing a Markov chain model within a hidden Markov models (HMMs) framework to harness an observed dependency relationship between concepts of a Java programming course. We found that hidden factors such as the age and gender of the learners affect their learning path, emphasizing the effectiveness of the underlying dependency relationship between the tested programming concepts. To better nurture a well-performing intelligent tutoring system, we provide a natural algorithmic approach that takes into account, beside existent concept dependencies, also individual characteristics of the learners, so as to minimize the learning time of learners and enhance the system’s efficiency.

Despite their known weaknesses, hidden Markov models (HMMs) have been the dominant technique for acoustic modeling in speech recognition for over two decades. Still, the advances in the HMM framework have not solved its key problems: it discards information about time dependencies and is prone to overgeneralization. In this paper, we attempt to overcome these problems by relying on straightforward template matching. The basis for the recognizer is the well-known DTW algorithm. However, classical DTW continuous speech recognition results in an explosion of the search space. The traditional top-down search is therefore complemented with a data-driven selection of candidates for DTW alignment. We also extend the DTW framework with a flexible subword unit mechanism and a class sensitive distance measure-two components suggested by state-of-the-art HMM systems. The added flexibility of the unit selection in the template-based framework leads to new approaches to speaker and environment adaptation. The template matching system reaches a performance somewhat worse than the best published HMM results for the Resource Management benchmark, but thanks to complementarity of errors between the HMM and DTW systems, the combination of both leads to a decrease in word error rate with 17% compared to the HMM results

This study is designed to investigate the feasibility of automatic sleep staging using features only derived from electrocardiography (ECG) signal. The study was carried out using the framework of hidden Markov models (HMMs). The mean, and SD values of heart rates (HRs) computed from each 30-second epoch served as the features. The two feature sequences were first detrended by ensemble empirical mode decomposition (EEMD), formed as a two-dimensional feature vector, and then converted into code vectors by vector quantization (VQ) method. The output VQ indexes were utilized to estimate parameters for HMMs. The proposed model was tested and evaluated on a group of healthy individuals using leave-one-out cross-validation. The automatic sleep staging results were compared with PSG estimated ones. Results showed accuracies of 82.2%, 76.0%, 76.1% and 85.5% for deep, light, REM and wake sleep, respectively. The findings proved that HRs-based HMM approach is feasible for automatic sleep staging and can pave a way for developing more efficient, robust, and simple sleep staging system suitable for home application.

Among speech researchers, it is widely believed that Hidden Markov Models (HMMs) are the most successful modelling approaches for acoustic events in speech recognition. However, common assumptions limit the classification abilities of HMMs and these can been relaxed by introducing neural networks in the HMM framework. With today's advances in VLSI technology, artificial neural networks (ANNs) can be integrated into a single chip offering adequate circuit complexity required to attain both a high recognition accuracy and an improved learning time. Analogue implementations are considered due to the high processing speeds. The relative performance of different speech coding parameters for use with two different ANN architectures that lend themselves to analogue hardware implementations are investigated. In this case, the dynamic ranges of the different coefficients need to be taken into consideration since they will affect the performance of the analogue chip due to the scaling of the coefficients to voltage signals. The hardware requirements for implementing the two architectures are then discussed.

In this dissertation, a novel approach of integrating template matching with statistical modeling is proposed to improve continuous speech recognition. Hidden Markov Modeling (HMMs) has been the dominant approach in statistical speech recognition since it provides a principled way of jointly modeling speech spectral variations and time dynamics. However, HMMs have the shortcoming of assuming the observations being independent within each state, which makes it ineffective in modeling the details of speech temporal evolutions that are important for characterizing nonstationary speech sounds. Template-based methods make comparisons between a test pattern and the templates derived from training data, and therefore they are able to capture speech dynamics and time correlation of speech frames better than HMM based methods. However, template matching requires large memory space and computational time since feature vectors of training data need to be stored in computer memory for access at the recognition stage, which is difficult in large vocabulary continuous speech recognition (LVCSR). Our proposed approach takes advantages of both statistical modeling and template matching, which overcomes the weakness of conventional template-based method and is feasible for LVCSR. We use multiple Gaussian Mixture Model (GMM) indices to represent each frame of speech templates, and define the template unit to be context-dependent phone segments (triphone context). We also use phonetic decision trees borrowed from those commonly used in HMMs to tie triphone templates and predict triphones unseen in training data. Two local distances, log likelihood ratio (LLR) and Kullback-Leibler (KL) divergence, are proposed for dynamic time warping (DTW) based template matching. In order to reduce computational complexity and storage space, we propose methods of minimum distance template selection (MDTS) and maximum log-likelihood template selection (MLTS), and investigate a template compression method on top of template selection to further improve recognition performance. The template based methods were used to rescore lattices generated by baseline HMMs on the tasks of TIMIT continuous phone recognition and teleheath LVCSR and experimental results demonstrated that the proposed approach of integrating template matching with statistical modeling significantly improved recognition performances over the HMM baselines. The template selection methods also provided significant recognition accuracy improvements over the HMM baseline while largely reducing the computation and storage complexities. When all templates or MDTS were used, using the LLR local distance obtained better recognition performance than the KL divergence local distance. For MLTS and template compression, KL divergence local distance provided better performance than the LLR local distance, and the template compression method made further improvements over KL based MLTS. Since the templates were constructed based on the GMM indices extracted from HMM baselines, we also validated the effectiveness of the proposed template methods based on enhanced HMM baselines. Experimental results showed that LLR based all template method was able to consistently improve TIMIT phone recognition accuracies based on four enhanced HMM baselines. Prosodic features such as duration, energy, and pitch can reflect longer span information of speech than conventional single frame vectors but they have commonly been ignored by HMMs. Template based methods provide possibilities to conveniently integrate prosodic features into speech recognition, which has not been well studied in the past. In this dissertation, we investigate combining template based methods with the speech prosodic features of duration, energy and pitch to further improve speech recognition accuracy. The scores of prosodic information were computed by a GMM based method and a non-parametric method, and the prosodic scores were combined with the acoustic scores in triphone template matching. Experimental results obtained on the telehealth task showed that prosodic information had positive effects on vowel sound recognition.

In this paper, a new algorithm for text-dependent speaker verification is presented. The algorithm uses a set of concatenated Neural Tree Networks (NTNs) trained with sub-word units for speaker verification. The conventional NTN when trained by all the words in training data achieves good results in the text-independent task. The proposed method is described as follows. First, the predetermined password in the training data is segmented into sub-word units by Hidden Markov Model (HMM). Second, an NTN is trained for only the data segmented into that sub-word unit. It integrates the discriminatory ability of NTN with the framework of HMMs which demonstrates ability in modeling temporal variation of speech. The sub-word NTN trained with clustered data reduces the complexity of the NTN structure, and is more powerful in discriminating speakers. This new algorithm was evaluated by experiments on a TI isolated-word database, which contains 16 speakers. An improvement of performance was obtained over baseline performance obtained from conventional methods.

Proposes a global acoustic segment model for characterizing fundamental speech sound units and their interactions based upon a general framework of hidden Markov models (HMM). Each segment model represents a class of acoustically similar sounds. The intra-segment variability of each sound class is modeled by an HMM, and the sound-to-sound transition rules are characterized by a probabilistic intersegment transition matrix. An acoustically-derived lexicon is used to construct word models based upon subword segment models. The proposed segment model was tested on a speaker-trained, isolated word, speech recognition task with a vocabulary of 1109 basic English words. In the current study, only 128 segment models were used, and recognition was performed by optimally aligning the test utterance with all acoustic lexicon entries using a maximum likelihood Viterbi decoding algorithm. Based upon a database of three male speakers, the average word recognition accuracy for the top candidate was 85% and increased to 96% and 98% for the top 3 and top 5 candidates, respectively. >

This paper describes a method for improving handwritten word recognition by implicitly recognizing the writing style. Writing style is taken here to cover several types of distinctions between word shapes: cursive script vs. handprinted words, run-on vs. discrete words, differences in skew angle values, stability of lower and upper extensions of letters, presence or absence of loops in naturally looped letters. This method is applied in the general framework of hidden Markov models (HMM). The proposed method consists in the use of a set of models rather than of a unique model for each word. Each model in the set is associated to a certain class of writers, As a consequence, writing style is automatically and implicitly detected during recognition. But the main contribution of the method is a better estimation of the recognition score, i.e. the probability of generating the word with the HMM.

In recent years, automatic map matching has received great technical progress. However, when it comes to vague matching situations such as improper vocabulary use, there still lack reliable solutions. To handle the current gap, this paper proposes a novel automatic map matching method based on the hybrid computing framework of hidden Markov model (HMM) and conditional random field. First, the data filtering is completed by performing second-order transformation towards automatic matching conditions of HMM. Then, the data classification is completed using automatic data classification based on the conditional random field. After that, a hybrid computing framework with spatial elements and layer selection is built to generate map matching results. Finally, some simulation experiments are conducted for evaluation. For one thing, the trend of matching accuracy changes under specified conditions is basically the same as that of nonspecified conditions. The maximum difference in matching calculation values is about 3 times. However, once the vocabulary continues to increase, the difference in matching results between the two narrows to 10–20%. For the other thing, the matching accuracy of a specified state is higher than that of sending a specified state. While nonspecified fuzzy matching accuracy is about 3 times higher and nonspecified precision matching accuracy is about 50% higher.

Hidden Markov models with factored Gaussian mixtures densities

The present paper describes a corpus-based singing voice syn-thesis system based on hidden Markov models (HMMs). Thissystem employs the HMM-based speech synthesis to synthesizesingingvoice. Musical information such aslyrics, tones, durationsis modeled simultaneously in a unified framework of the context-dependent HMM. It can mimic the voice quality and singing styleof the original singer. Results of a singing voice synthesis exper-iment show that the proposed system can synthesize smooth andnatural-sounding singing voice. Index Terms : singing voice synthesis, HMM, time-lag model. 1. Introduction In recent years, various applications of speech synthesis systemshave been proposed and investigated. Singing voice synthesis isone of the hot topics in this area [1–5]. However, only a fewcorpus-based singing voice synthesis systems which can be con-structed automatically have been proposed.Currently, there are two main paradigms in the corpus-basedspeech synthesis area: sample-based approach and statistical ap-proach. The sample-based approach such as unit selection [6]can synthesize high-quality speech. However, it requires a hugeamountoftrainingdatatorealizevariousvoicecharacteristics. Onthe other hand, the quality of statistical approach such as HMM-basedspeechsynthesis[7]isbuzzybecauseitisbasedonavocod-ingtechnique. However,itissmoothandstable,anditsvoicechar-acteristics can easily be modified by transforming HMM parame-ters appropriately. For singing voice synthesis, applying the unitselection seems to be difficult because a huge amount of singingspeech which covers vast combinations of contextual factors thataffect singing voice has to be recorded. On the other hand, theHMM-based system can be constructed using a relatively smallamount of training data. From this point of view, the HMM-basedapproach seems to be more suitable for the singing voice synthe-sizer. In the present paper, we apply the HMM-based synthesisapproach to singing voice synthesis.Although the singing voice synthesis system proposed in thepresent paper is quite similar to the HMM-based text-to-speechsynthesissystem[7],therearetwomaindifferencesbetweenthem.In the HMM-based text-to-speech synthesis system, contextualfactors which may affect reading speech (e.g. phonemes, sylla-bles, words, phrases, etc.) are taken into account. However, con-textual factors which may affect singing voice should be different

In the field of Natural Language Processing, one of the very important research areas of Information Extraction (IE) comes in Named Entity Recognition (NER). NER is a subtask of IE that seeks to identify and classify the predefined categories of named entities in text documents. Considerable amount of work has been done on NER in recent years due to the increasing demand of automated texts and the wide availability of electronic corpora. While it is relatively easy and natural for a human reader to read and understand the context of a given article, getting a machine to understand and differentiate between words is a big challenge. For instance, the word ‘brown’ may refer to a person called Mr. Brown, or the colour of an item which is brown. Human readers can easily discern the meaning of the word by looking at the context of that particular sentence, but it would be almost impossible for a computer to interpret it without any additional information. To deal with the issue, researchers in NER field have proposed various rule-based systems (Wakao, Gaizauskas & Wilks, 1996; Krupka & Hausman, 1998; Maynard, Tablan, Ursu, Cunningham & Wilks, 2001). These systems are able to achieve high accuracy in recognition with the help of some lists of known named entities called gazetteers. The problem with rule-based approach is that it lacks the robustness and portability. It incurs steep maintenance cost especially when new rules need to be introduced for some new information or new domains. A better option is thus to use machine learning approach that is trainable and adaptable. Three wellknown machine learning approaches that have been used extensively in NER are Hidden Markov Model (HMM), Maximum Entropy Model (MEM) and Decision Tree. Many of the existing machine learning-based NER systems (Bikel, Schwartz & Weischedel, 1999; Zhou & Su, 2002; Borthwick, Sterling, Agichten & Grisham, 1998; Bender, Och & Ney, 2003; Chieu & Ng, 2002; Sekine, Grisham & Shinnou, 1998) are able to achieve near-human performance for named entity tagging, even though the overall performance is still about 2% short from the rule-based systems. There have also been many attempts to improve the performance of NER using a hybrid approach with the combination of handcrafted rules and statistical models (Mikheev, Moens & Grover, 1999; Srihari & Li, 2000; Seon, Ko, Kim & Seo, 2001). These systems can achieve relatively good performance in the targeted domains owing to the comprehensive handcrafted rules. Nevertheless, the portability problem still remains unsolved when it comes to dealing with NER in various domains. As such, this article presents a hybrid machine learning approach using MEM and HMM successively. The reason for using two statistical models in succession instead of one is due to the distinctive nature of the two models. HMM is able to achieve better performance than any other statistical models, and is generally regarded as the most successful one in machine learning approach. However, it suffers from sparseness problem, which means considerable amount of data is needed for it to achieve acceptable performance. On the other hand, MEM is able to maintain reasonable performance even when there is little data available for training purpose. The idea is therefore to walkthrough the testing corpus using MEM first in order to generate a temporary tagging result, while this procedure can be simultaneously used as a training process for HMM. During the second walkthrough, the corpus uses HMM for the final tagging. In this process, the temporary tagging result generated by MEM will be used as a reference for subsequent error checking and correction. In the case when there is little training data available, the final result can still be reliable based on the contribution of the initial MEM tagging result.

This paper presents an original hidden Markov model (HMM) approach for online beat segmentation and classification of electrocardiograms. The HMM framework has been visited because of its ability of beat detection, segmentation and classification, highly suitable to the electrocardiogram (ECG) problem. Our approach addresses a large panel of topics some of them never studied before in other HMM related works: waveforms modeling, multichannel beat segmentation and classification, and unsupervised adaptation to the patient's ECG. The performance was evaluated on the two-channel QT database in terms of waveform segmentation precision, beat detection and classification. Our waveform segmentation results compare favorably to other systems in the literature. We also obtained high beat detection performance with sensitivity of 99.79% and a positive predictivity of 99.96%, using a test set of 59 recordings. Moreover, premature ventricular contraction beats were detected using an original classification strategy. The results obtained validate our approach for real world application.

We consider distributed parameter estimation using quantized observations in wireless sensor networks (WSN) operating in a noisy channel environment. Due to bandwidth constraints, each sensor quantizes its local observation into one bit of information. Previously, adaptive quantization(AQ) schemes were developed under the assumption of perfect communication links between the sensors and the fusion center (FC). In this paper we propose an adaptive quantization scheme for a WSN with channel links modeled as binary erasure channels. A first-order Hidden Markov Model (HMM) framework is introduced to model the adaptive quantization scheme. The introduction of a HMM framework aids in the systematic design of an estimator. To address the significant problem of bit erasures, we propose an Expectation-Maximization (EM) based estimator. Theoretical closed form solutions for the Cramer-Rao lower bounds are developed for the proposed estimation problem under certain assumptions. We analyze the performance of the proposed quantization scheme and estimator under different criteria. Numerical simulation results are shown for the proposed adaptive quantization and EM parameter estimation scheme under different scenarios. The simulation results indicate that the proposed quantization scheme and estimator are robust and can provide superior performance for erasure rates up to 10 %.