Application of the Gibbs distribution to hidden Markov modeling inspeaker independent isolated word recognition

A method of integrating the Gibbs distributions (GDs) into hidden Markov models (HMMs) is presented. The probabilities of the hidden state sequences of HMMs are modeled by GDs in place of the transition probabilities. The GDs offer a general way in modeling neighbor interactions of Markov random fields where the Markov chains in HMMs are special cases. An algorithm for estimating the model parameters is developed based on Baum reestimation, and an algorithm for computing the probability terms is developed using a lattice structure. The GD models were used for experiments in speech recognition on the TI speaker-independent, isolated digit database. The observation sequences of the speech signals were modeled by mixture Gaussian autoregressive densities. The energy functions of the GDs were developed using very few parameters and proved adequate in hidden layer modeling. The results of the experiments showed that the GD models performed at least as well as the HMM models     

Real-time discrimination of ventricular tachyarrhythmia withFourier-transform neural network

The authors have developed a method to discriminate life-threatening ventricular arrhythmias by observing the QRS complex of the electrocardiogram (ECG) in each heartbeat. Changes in QRS complexes due to rhythm origination and conduction path were observed with the Fourier transform, and three kinds of rhythms were discriminated by a neural network. In this paper, the potential of the authors' method for clinical uses and real-time detection was examined using human surface ECGs and intracardiac electrograms (EGMs). The method achieved high sensitivity and specificity (>0.98) in discrimination of supraventricular rhythms from ventricular ones. The authors also present a hardware implementation of the algorithm on a commercial single-chip CPU     

QRS feature extraction using linear prediction

This communication proposes a method called linear prediction (a high performant technique in digital speech processing) for analyzing digital ECG signals. There are several significant properties indicating that ECG signals have an important feature in the residual error signal obtained after processing by Durbin's linear prediction algorithm. This communication also indicates that the prediction order need not be more than two for fast arrhythmia detection. The ECG signal classification puts an emphasis on the residual error signal. For each ECG's QRS complex, the feature for recognition is obtained from a nonlinear transformation which transforms every residual error signal to a set of three states pulse-code train relative to the original ECG signal. The pulse-code train has the advantage of easy implementation in digital hardware circuits to achieve automated ECG diagnosis. The algorithm performs very well in feature extraction in arrhythmia detection. Using this method, our studies indicate that the PVC (premature ventricular contraction) detection has at least a 92 percent sensitivity for MIT/BIH arrhythmia database.     

Mandarin tone recognition based on wavelet transform and hidden Markov modeling

This paper presents a method of tone recognition for Mandarin speech by using combination of wavelet transform and hidden Markov modeling techniques. A pitch detector based on singularity detection and multi-resolution analysis of wavelet transform is employed for estimation of pitch periods, and hidden Markov modeling with partition Gaussian mixtures probability density function is used for the tone recognition. The algorithm can provide recognition accuracy of 97.22% and 94.47% for speaker-dependent and speaker-independent tone recognition, respectively.     

Atrial activity enhancement by Wiener filtering using an artificial neural network

This paper describes a novel technique for the cancellation of the ventricular activity for applications such as P-wave or atrial fibrillation detection. The procedure was thoroughly tested and compared with a previously published method, using quantitative measures of performance. The novel approach estimates, by means of a dynamic time delay neural network (TDNN), a time-varying, nonlinear transfer function between two ECG leads. Best results were obtained using an Elman TDNN with nine input samples and 20 neurons, employing a sigmoidal tangencial activation in the hidden layer and one linear neuron in the output stage. The method does not require a previous stage of QRS detection. The technique was quantitatively evaluated using the MIT-BIH arrhythmia database and compared with an adaptive cancellation scheme proposed in the literature. Results show the advantages of the proposed approach, and its robustness during noisy episodes and QRS morphology variations.     

采用HDPHMM符号化器的语音查询样例检测方法

提出一种基于层级狄利克雷过程隐马尔科夫模型（HDPHMM）符号化器的无监督语音查询样例检测（QbE-STD）方法。该方法首先应用一个双状态层隐马尔科夫模型,其中顶层状态用于表示所发现的声学单元,底层状态用于建模顶层状态的发射概率,通过对顶层状态假设一个层级狄利克雷过程先验,获得非参贝叶斯模型HDPHMM。使用无标注语音数据对该模型进行训练,然后对测试语音和查询样例输出后验概率特征矢量,使用非负矩阵分解算法对后验概率进行优化得到新的特征,然后在此基础上,应用修正分段动态时间规整算法进行检索,构成QbE-STD系统。实验结果表明,相比于基于高斯混合模型符号化器的基线系统,本文所提出的方法性能更优,检索精度得到显著提升。      

Neural-network-based adaptive matched filtering for QRS detection

We have developed an adaptive matched filtering algorithm based upon an artificial neural network (ANN) for QRS detection. We use an ANN adaptive whitening filter to model the lower frequencies of the ECG which are inherently nonlinear and nonstationary. The residual signal which contains mostly higher frequency QRS complex energy is then passed through a linear matched filter to detect the location of the QRS complex. We developed an algorithm to adaptively update the matched filter template from the detected QRS complex in the ECG signal itself so that the template can be customized to an individual subject. This ANN whitening filter is very effective at removing the time-varying, nonlinear noise characteristic of ECG signals. Using this novel approach, the detection rate for a very noisy patient record in the MIT/BIH arrhythmia database is 99.5%, which compares favorably to the 97.5% obtained using a linear adaptive whitening filter and the 96.5% achieved with a bandpass filtering method.     

基于生成对抗网络的动态心电信号QRS波检测

心电信号分析是预防心血管疾病的重要举措,QRS波的精确检测不仅是心电信号处理的关键步骤且对心率计算和异常情况分析具有重要作用.针对动态心电信号存在信号质量差或异常节奏波形导致常用QRS波检测方法精度较低的问题,本文提出了 一种基于生成对抗网络新型QRS波检测算法.该算法以Pix2Pix网络为基础,生成网络采用U-Net...     

Gain-adapted hidden Markov models for recognition of clean andnoisy speech

In applying hidden Markov modeling for recognition of speech signals, the matching of the energy contour of the signal to the energy contour of the model for that signal is normally achieved by appropriate normalization of each vector of the signal prior to both training and recognition. This approach, however, is not applicable when only noisy signals are available for recognition. A unified approach is developed for gain adaptation in recognition of clean and noisy signals. In this approach, hidden Markov models (HMMs) for gain-normalized clean signals are designed using maximum-likelihood (ML) estimates of the gain contours of the clean training sequences. The models are combined with ML estimates of the gain contours of the clean test signals, obtained from the given clean or noisy signals, in performing recognition using the maximum a posteriori decision rule. The gain-adapted training and recognition algorithms are developed for HMMs with Gaussian subsources using the expectation-minimization (EM) approach     

基于MATLAB的语音增强系统的设计

语音增强是信号处理领域中的一个重要的组成部分。在许多语音处理的应用中,例如移动通信,语音识别和助听器,语音信号的处理不得不在具有噪声的环境下进行。在过去的几十年里,人们提出了许多方法去消除噪声和减少语音失真,例如谱减法,基于小波的方法,隐式马尔科夫模型法和信号子空间法等。小波分析由于能同时在时域和频域中对信号进行分析,所以它能有效地实现对信号的去噪。介绍了一种语音增强系统的设计方法,采用Least Mean Square（LMS）算法和小波变换相结合的方法对带噪语音进行去噪,并在MATLAB的Simulink环境下建立了该系统的模型。通过对该模型的仿真表明：该方法去噪效果明显,为该系统在硬件上的实现打下了理论基础。     

ECG signal analysis through hidden Markov models

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.     

基于小波变换的QRS波群检测

提出了一种基于小波多分辨分析的算法,对心电信号进行特征提取和识别。通过小波变换对常规心电图信号进行分解去噪和特征提取,并利用动态自适应阈值和删除多检点,补偿漏检点对QRS波检测进行优化。实验结果表明该方法在QRS波形不失真的情况下,提高了一部分MIT-BIH数据库信号中QRS波识别的准确率,并且对于较低准确率的心电信号的原因进行了分析。     

Hybrid approach to speech recognition using hidden Markov modelsand Markov chains

The paper presents a hybrid of a hidden Markov model and a Markov chain model for speech recognition. In this hybrid, the hidden Markov model is concerned with the time-varying property of spectral features, while the Markov chain accounts for the interdependence of spectral features. The log-likelihood scores of the two models, with respect to a given utterance, are combined by a postprocessor to yield a combined log-likelihood score for word classification. Experiments on speaker-independent and multispeaker isolated English alphabet recognition show that the hybrid outperformed both the hidden Markov model and the Markov chain model in terms of recognition     

Speech recognition algorithm based on neural network and hidden Markov model

This study proposes a hybrid model of speech recognition parallel algorithm based on hidden Markov model (HMM) and artificial neural network (ANN). First, the algorithm uses HMM for time-series modeling of speech signals and calculates the voice to the HMM of the output probability score. Second, with the probability score as input to the neural network, the algorithm gets information for classification and recognition and makes a decision based on the hybrid model. Finally, Matlab software is used to train and test sample data. Simulation results show that using the strong time-series modeling ability of HMM and the classification features of neural network, the proposed algorithm possesses stronger noise immunity than the traditional HMM. Moreover, the hybrid model enhances the individual flaws of the HMM and the neural network and greatly improves the speed and performance of speech recognition.     

Development of an acoustic-phonetic hidden Markov model forcontinuous speech recognition

The techniques used to develop an acoustic-phonetic hidden Markov model, the problems associated with representing the whole acoustic-phonetic structure, the characteristics of the model, and how it performs as a phonetic decoder for recognition of fluent speech are discussed. The continuous variable duration model was trained using 450 sentences of fluent speech, each of which was spoken by a single speaker, and segmented and labeled using a fixed number of phonemes, each of which has a direct correspondence to the states of the matrix. The inherent variability of each phoneme is modeled as the observable random process of the Markov chain, while the phonotactic model of the unobservable phonetic sequence is represented by the state transition matrix of the hidden Markov model. The model assumes that the observed spectral data were generated by a Gaussian source. However, an analysis of the data shows that the spectra for the most of the phonemes are not normally distributed and that an alternative representation would be beneficial     

一种基于小波变换和隐Markov模型的声调识别方法

本文给出了一种基于小波变换和隐Markov模型(HMM)的声调识别方法。根据小波变换检测信号突变的性质,充分利用多分辨率分析,准确可靠地实现了基音检测;采用分划Gauss混合(PGM)概率密度函数的HMM进行汉语声调识别,推导出用PGM函数的Viterbi算法的简化递推式。在匹配计算量大大减小的情况下,特定人的四声识别率为97.22％,非特定人达到94.47％。     

Nonstationary harmonic modeling for ECG removal in surface EMG signals

We present a compact approach for mitigating the presence of electrocardiograms (ECG) in surface electromyographic (EMG) signals by means of time-variant harmonic modeling of the cardiac artifact. Heart rate and QRS complex variability, which often account for amplitude and frequency time variations of the ECG, are simultaneously captured by a set of third-order constant-coefficient polynomials modulating a stationary harmonic basis in the analysis window. Such a characterization allows us to significantly suppress ECG from the mixture by preserving most of the EMG signal content at low frequencies (less than 20?Hz). Moreover, the resulting model is linear in parameters and the least-squares solution to the corresponding linear system of equations efficiently provides model parameter estimates. The comparative results suggest that the proposed method outperforms two reference methods in terms of the EMG preservation at low frequencies.     

Estimation accuracy of P wave and QRS complex occurrence times in the ECG: The accuracy for simplified theoretical and computer simulated waveforms

One of the main points of interest in the study of the dynamic behaviour of ECG time intervals is the accuracy with which characteristic moments can be estimated in the various waveform segments such as the P wave or QRS complex. In this study, the error involved in such estimation is regarded as due to the superposition of various types of disturbances (noise, hum and fluctuations in amplitude and symmetry) on a supposedly ideal ECG waveform. The effect of these disturbances on estimation accuracy is investigated for three estimation methods (peak estimation, double level estimation and matched filter estimation) by two different approaches; one based on use of a highly simplified theoretical model permitting the derivation of mathematical expressions for the estimation error, and one involving computer-aided simulation of ECG waveforms, based on real ECG data, with various types of disturbances on the basis of recorded ECG data. Both approaches indicate that noise and hum make the main contribution to estimation error, and that matched filter estimation is likely to give best estimation accuracy for both P waves and QRS complexes.     

A Real-Time QRS Detection Algorithm

We have developed a real-time algorithm for detection of the QRS complexes of ECG signals. It reliably recognizes QRS complexes based upon digital analyses of slope, amplitude, and width. A special digital bandpass filter reduces false detections caused by the various types of interference present in ECG signals. This filtering permits use of low thresholds, thereby increasing detection sensitivity. The algorithm automatically adjusts thresholds and parameters periodically to adapt to such ECG changes as QRS morphology and heart rate. For the standard 24 h MIT/BIH arrhythmia database, this algorithm correctly detects 99.3 percent of the QRS complexes.     

Optimum MVF Estimation‐Based Two‐Band Excitation for HMM‐Based Speech Synthesis

The optimum maximum voiced frequency (MVF) estimation‐based two‐band excitation for hidden Markov model‐based speech synthesis is presented. An analysis‐by‐synthesis scheme is adopted for the MVF estimation which leads to the minimum spectral distortion of synthesized speech. Experimental results show that the proposed method significantly improves synthetic speech quality.