Speech recognition based on genetic algorithm for training HMM

Based on global optimisation, a new genetic algorithm for training hidden Markov models (HMMs) is proposed. The results of speech recognition are presented and a comparison made with the classic training HMM algorithm     

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     

基于不同隐马尔科夫模型的图像识别方法

为了更详细地研究隐马尔科夫模型在图像识别中的应用,以指纹识别为例,纵向总结了几种基于隐马尔科夫模型的指纹图像识别算法,包括一维隐马尔科夫模型、伪二维隐马尔科夫模型、二维模型及一维模型组。分别从时间复杂度、识别精确度等方面总结出这四种隐马尔科夫模型在图像识别时的优缺点,得出不同待识别图像适合使用的识别模型的结论。     

Modeling acoustic transitions in speech by state-interpolationhidden Markov models

The authors present a new type of hidden Markov model (HMM) for vowel-to-consonant (VC) and consonant-to-vowel (CV) transitions based on the locus theory of speech perception. The parameters of the model can be trained automatically using the Baum-Welch algorithm and the training procedure does not require that instances of all possible CV and VC pairs be present. When incorporated into an isolated word recognizer with a 75000 word vocabulary it leads to the modest improvement in recognition rates. The authors give recognition results for the state interpolation HMM and compare them to those obtained by standard context-independent HMMs and generalized triphone models     

Use of multiple vector quantisation for semicontinuous-HMM speechrecognition

Although the continuous hidden Markov model (CHMM) technique seems to be the most flexible and complete tool for speech modelling. It is not always used for the implementation of speech recognition systems because of several problems related to training and computational complexity. Thus, other simpler types of HMMs, such as discrete (DHMM) or semicontinuous (SCHMM) models, are commonly utilised with very acceptable results. Also, the superiority of continuous models over these types of HMMs is not clear. The authors' group has previously introduced the multiple vector quantisation (MVQ) technique, the main feature of which is the use of one separated VQ codebook for each recognition unit. The MVQ technique applied to DHMM models generates a new HMM modelling (basic MVQ models) that allows incorporation into the recognition dynamics of the input sequence information wasted by the discrete models in the VQ process. The authors propose a new variant of HMM models that arises from the idea of applying MVQ to SCHMM models. These are SCMVQ-HMM (semicontinuous multiple vector quantisation HMM) models that use one VQ codebook per recognition unit and several quantisation candidates for each input vector. It is shown that SCMVQ modelling is formally the closest one to CHMM, although requiring even less computation than SCHMMs. After studying several implementation issues of the MVQ technique. Such as which type of probability density function should be used, the authors show the superiority of SCMVQ models over other types of HMM models such as DHMMs, SCHMMs or the basic MVQs     

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     

基于HMMs的人体姿态图像视觉理解研究

利用隐马尔可夫模型(HMMs) ,对CCD摄像机采集的人体运动视频图像中的人体姿态识别问题进行了研究,主要内容包括选择新的特征向量抽取算法;设计HMM训练和识别算 法。实验结果表明,该方法在实践中是可行的。在虚拟现实、视觉监控、感知接口等领域均有着广阔的应用前景。     

Phonemic hidden Markov models with continuous mixture outputdensities for large vocabulary word recognition

The authors demonstrate the effectiveness of phonemic hidden Markov models with Gaussian mixture output densities (mixture HMMs) for speaker-dependent large-vocabulary word recognition. Speech recognition experiments show that for almost any reasonable amount of training data, recognizers using mixture HMMs consistently outperform those employing unimodal Gaussian HMMs. With a sufficiently large training set (e.g. more than 2500 words), use of HMMs with 25-component mixture distributions typically reduces recognition errors by about 40%. It is also found that the mixture HMMs outperform a set of unimodal generalized triphone models having the same number of parameters. Previous attempts to employ mixture HMMs for speech recognition proved discouraging because of the high complexity and computational cost in implementing the Baum-Welch training algorithm. It is shown how mixture HMMs can be implemented very simply in unimodal transition-based frameworks by allowing multiple transitions from one state to another     

Image segmentation using hidden Markov Gauss mixture models.

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum discrimination information (MDI) distortion. We formulate the image segmentation problem using a maximum a posteriori criteria and find the hidden states that maximize the posterior density given the observation. We estimate both the hidden Markov parameter and hidden states using a stochastic expectation-maximization algorithm. Our results demonstrate that HMGMM provides better classification in terms of Bayes risk and spatial homogeneity of the classified objects than do several popular methods, including classification and regression trees, learning vector quantization, causal hidden Markov models (HMMs), and multiresolution HMMs. The computational load of HMGMM is similar to that of the causal HMM.     

Maximum Likelihood Training and Adaptation of Embedded Speech Recognizers for Mobile Environments

For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.     

On state-estimation of a two-state hidden Markov model withquantization

We consider quantization from the perspective of minimizing filtering error when quantized instead of continuous measurements are used as inputs to a nonlinear filter, specializing to discrete-time two-state hidden Markov models (HMMs) with continuous-range output. An explicit expression for the filtering error when continuous measurements are used is presented. We also propose a quantization scheme based on maximizing the mutual information between quantized observations and the hidden states of the HMM     

A computationally efficient approach to the estimation of two- and three-dimensional hidden Markov models.

Statistical modeling methods are becoming indispensable in today's large-scale image analysis. In this paper, we explore a computationally efficient parameter estimation algorithm for two-dimensional (2-D) and three-dimensional (3-D) hidden Markov models (HMMs) and show applications to satellite image segmentation. The proposed parameter estimation algorithm is compared with the first proposed algorithm for 2-D HMMs based on variable state Viterbi. We also propose a 3-D HMM for volume image modeling and apply it to volume image segmentation using a large number of synthetic images with ground truth. Experiments have demonstrated the computational efficiency of the proposed parameter estimation technique for 2-D HMMs and a potential of 3-D HMM as a stochastic modeling tool for volume images.     

Isolated-utterance speech recognition using hidden Markov modelswith bounded state durations

Hidden Markov models (HMMs) with bounded state durations (HMM/BSD) are proposed to explicitly model the state durations of HMMs and more accurately consider the temporal structures existing in speech signals in a simple, direct, but effective way. A series of experiments have been conducted for speaker dependent applications using 408 highly confusing first-tone Mandarin syllables as the example vocabulary. It was found that in the discrete case the recognition rate of HMM/BSD (78.5%) is 9.0%, 6.3%, and 1.9% higher than the conventional HMMs and HMMs with Poisson and gamma distribution state durations, respectively. In the continuous case (partitioned Gaussian mixture modeling), the recognition rates of HMM/BSD (88.3% with 1 mixture, 88.8% with 3 mixtures, and 89.4% with 5 mixtures) are 6.3%, 5.0%, and 5.5% higher than those of the conventional HMMs, and 5.9% (with 1 mixture), 3.9% (with 3 mixtures) and 3.1% (with 1 mixture), 1.8% (with 3 mixtures) higher than HMMs with Poisson and gamma distributed state durations, respectively     

Modeling and classification of natural sounds by product codehidden Markov models

Linear predictive coding (LPC), vector quantization (VQ), and hidden Markov models (HMMs) are three popular techniques from speech recognition which are applied in modeling and classifying nonspeech natural sounds. A new structure called the product code HMM uses two independent HMM per class, one for spectral shape and one for gain. Classification decisions are made by scoring shape and gain index sequences from a product code VQ. In a series of classification experiments, the product code structure outperformed the conventional structure, with an accuracy of over 96% for three classes     

一种改进的隐马尔可夫模型训练方法及其在声目标识别中的应用

提出了一种基于最大相对界的改进隐马尔可夫模型训练方法.为解决隐马尔可夫模型的传统Baum_Welch训练算法在识别声目标时的局限以及现存区分训练算法泛化能力不足的问题,在经典隐马尔可夫模型为初始模型的基础上,定义了相对界,并通过最大化最小相对界建立一个最优化问题,用梯度下降法进行迭代求解,得到基于相对界的隐马尔可夫模型...     

Hidden Markov Models with Factored Gaussian Mixtures Densities

1　Introduction　Manyrealobserveddataarecharacterizedbymultiplecoupledcausesorfactors.Forinstance ,faceimagesmaybegeneratedbycombiningeyebrows,eyes ,noseandmouth .Similarly ,speechsignalsmayresultfromanin teractionofmotionsoffactorssuchasthejaw ,tongue ,velum ,lipandmouth .RecentlyZemelandHintonpro posedafactoriallearningarchitecture[1～ 2 ] todealwithfactorialdata .Thegoaloffactoriallearningistodiscov erthemultipleunderlyingcausesorfactorsfromtheob serveddataandfindarepresentationthatwillbo…     

A minimum discrimination information approach for hidden Markovmodeling

An iterative approach for minimum-discrimination-information (MDI) hidden Markov modeling of information sources is proposed. The approach is developed for sources characterized by a given set of partial covariance matrices and for hidden Markov models (HMMs) with Gaussian autoregressive output probability distributions (PDs). The approach aims at estimating the HMM which yields the MDI with respect to all sources that could have produced the given set of partial covariance matrices. Each iteration of the MDI algorithm generates a new HMM as follows. First, a PD for the source is estimated by minimizing the discrimination information measure with respect to the old model over all PDs which satisfy the given set of partial covariance matrices. Then a new model that decreases the discrimination information measure between the estimated PD of the source and the PD of the old model is developed. The problem of estimating the PD of the source is formulated as a standard constrained minimization problem in the Euclidean space. The estimation of a new model given the PD of the source is done by a procedure that generalizes the Baum algorithm. The MDI approach is shown to be a descent algorithm for the discrimination information measure, and its local convergence is proved     

On-line identification of hidden Markov models via recursiveprediction error techniques

An on-line state and parameter identification scheme for hidden Markov models (HMMs) with states in a finite-discrete set is developed using recursive prediction error (RPE) techniques. The parameters of interest are the transition probabilities and discrete state values of a Markov chain. The noise density associated with the observations can also be estimated. Implementation aspects of the proposed algorithms are discussed, and simulation studies are presented to show that the algorithms converge for a wide variety of initializations. In addition, an improved version of an earlier proposed scheme (the Recursive Kullback-Leibler (RKL) algorithm) is presented with a parameterization that ensures positivity of transition probability estimates