A segment model based approach to speech recognition

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.

In this letter, we propose a new trajectory model for characterizing segmental features and their interaction based upon a general framework of hidden Markov models. Each segment, a sequence of frame vectors, is represented by a trajectory of observed vector sequences. This trajectory replaces the frame features in the segment and becomes the input of the segmental hidden Markov models (HMM's). In our approach, we adopt polynomial trajectory modeling to represent the trajectories using a new design matrix that includes transitional information on neighborhood acoustic events. To apply this trajectory to the segmental HMM, extra- and intrasegmental variations are modified to contain trajectory information. The presented model is regarded as an extension and generalization of conventional HMM, trajectory-based segmental HMM, and parametric trajectory models. The experimental results are reported on the TIMIT corpus and performance is shown to improve significantly over that of the conventional 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.

A perceptually plausible solution to the problem of automatic recognition of speech in arbitrary noise backgrounds involves computational auditory scene analysis (ASA) followed by recognition of the separated patterns. However, it is not generally possible to recover a complete representation of individual acoustic sources, so a new approach is required to recognize partial descriptions. Suitable modifications to the powerful stochastic framework of hidden Markov models (HMM) have recently been described [M. P. Cooke, P. D. Green, and M. D. Crawford, Proc. Int. Conf. Spoken Language Processing (1994)]. The studies reported here demonstrate HMM-based digit recognition in noise. An auditory-nerve firing rate representation undergoes auditory scene analysis, producing a mask of time-frequency locations where the speech is dominant. Each mask frame defines a marginal distribution for the HMM probability calculation. Results show robust performance even when the mask has most of its elements removed. Further, these studies suggest a solution to the problem of sensitivity to F0 in matching auditory representations of speech in which F1 is represented by a set of resolved harmonics. The new approach ensures that the matching process operates on a partial description consisting largely of harmonic peaks.

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.

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 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.

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.

Hidden Markov models (HMMs) have become within a few years the main technology for online handwritten word recognition (HWR). We consider segment models which generalize HMMs, these models aim at modeling the signal at a global level rather than at the frame level and have been shown to overcome standard HMMs in their modeling ability. We propose a segment model which allows us to automatically handle different writing styles. We compare our system on the isolated character set of the UNIPEN database with a reference system and a baseline segment model.

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 %.

The microsegmental modeling methods for speech recognition is extended, and a novel approach based on a phonetic feature description of microstructural characteristics of speech segments is presented. The hidden Markov model (HMM) framework is used to provide the recognition algorithm, which assumes that the underlying Markov chain tracks the evolution of a set of features related to articulatory phenomena. Use of phonetic features as the primary speech units provides a framework where the HMM structure can be designed with the guidance of detailed speech knowledge. Details of such a design are shown for a stop-consonant-vowel vocabulary. Experimental results on the task of stop-consonant discrimination demonstrate the effectiveness of this model. The error rates are reduced by over 30% compared with the conventional HMM-based recognition methods using words, phones, and microsegments as the primary speech units.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Much of the progress in automatic speech recognition is attributable to the use of hidden Markov models (HMMs) to characterize acoustic speech patterns. Despite their success, HMMs make little use of knowledge about the speech signal, and variation that may be explicable in terms of the physical properties of the human speech production system is treated as random. There is, therefore, a need to develop a speech modeling paradigm which reflects human speech processes more closely. Segmental hidden Markov models (HMMs) are extended versions of conventional HMMs in which states are associated with sequences of observation vectors rather than individual vectors. By treating a segment as a homogeneous unit, dependencies between vectors within a segment can be modeled explicitly. This letter describes a segmental HMM in which a segment is modeled as a noisy function of a linear trajectory. The basic theory of the model is presented, together with formulae for model parameter optimization.

Recent research on biomedical signal processing especially ECG analysis mostly focused on the use of Hidden Markov Models (HMM). The general aim of any signal segmentation method is to partition a given signal into consecutive regions of interest. In the context of the ECG then, the role of segmentation is to determine as accurately as possible the onset and offset boundaries, as well as the peak locations, of the various waveform features, such that the ECG interval measurements may be computed automatically and the study of waveform patterns will be facilitated (Sayadi & Shamsollahi, 2009). Ad hoc algorithms have been developed in order to help cardiologists to segment large amounts of ECGs. But these algorithms do not provide a precise segmentation, and repetitive corrections have to be made. Wavelet parametrisation is known to highlight discontinuities in the signal, and has proven to give good results for ECG segmentation (Kawaja et al., 2006; Thomas et al., 2006). A statistical model helps to regularize the detection, resulting in a more robust delineation. One of the advantages of probabilistic models over traditional methods is that a confidence measure for each segmented signal is given by the log likelihood of the observed signal given the model (Thomas et al., 2006). The main focus of this chapter is to introduce some new and robust HMM associated with wavelet transform based methods for ECG analysis. The chapter begins with a review of the literature on the use of HMM to analyse ECG signals. We then consider in detail the suitability of HMM to provide a faithful statistical description of the ECG. In particular, we examine the validity of the various assumptions inherent in the HMM framework in the context of the ECG. Following this, we consider a number of specific issues in developing an HMM for ECG segmentation, including the choice of model architecture, type of observation models. Then a combination of HMM approach with wavelet properties will be explained.

Multivariate time series anomaly detection: A framework of Hidden Markov Models

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.