正反向隐马尔可替模型及其在连续语音识别中的应用

本文针对语音信号中客观存在的正、反向依赖特性，明确提出了用条件概率的概念来定量表述语音信号的这种正、反向的马尔可夫依赖关系，提出了描述语音信号这种正反向依赖关系的正反隐马可夫模型，并实验证明了仅仅利用语音反向依赖关系语音识别同样也能获得相当可观的识别性能。     

基于3维空间Viterbi算法的汉语连续语音识别方法

本文提出了基于３维空间Ｖｉｔｅｒｂｉ算法的汉语连续语音识别方法。本方法采用６０个音素单位的隐马尔可大模型（ＨＭＭ）和８个声调单位的ＨＭＭ作为识别用基元模型。音素基元模型和声调基元模型的识别结果的统合,采用音素单位的ＨＭＭ状态,声调单位的ＨＭＭ状态和时间的３维空间Ｖｉｔｅｒｂｉ算法来实现。     

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Ｍａａｒｋｏｖ模型的声调识别方法，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长法的简化递推式。     

一种CDHMM／MLP混合模型及其在语音识别中的应用

本文提出了一种由连续隐马尔可夫模型与多层感知器构成的混合模型，并将该模型应用于语音孤立词识别，这种混合模型首先用ＣＤＨＭＭ来获取输入信号的动态特性，然后再以ＭＬＰ分类器对输入信号进行分类识别。其主要目的是通过ＭＬＰ分类器，对ＣＤＨＭＭ中的似然估计值进行分析，分类，以加强和提高ＣＤＨＭＭ的分类能力。根据这种混合模型，我们建立了一个含３０个英语单词的语音识别系统。实验结果表明，该系统的识别率明显高于传     

特定人汉语数码语音抗噪识别方法

本文提出一种连续隐邓尔可夫模型（ＣＨＭＭ）和人工神经网络（ＡＮＮ）相结合的鲁棒性识别方法。用于噪声环境下特定人数码语音识别,该方法以ＣＨＭＭ的输出作为系统的识别矢量,利用人工神经网络的模式分类和自学习功能,从识别矢量空间中提取语音预识别矢量,再由识别结果进行识别输出。实验证明,这种基于ＣＨＭＭＡＮＮ的数码语音识别方法明显地提高了系统的噪声鲁棒性,适用于中小词表语音识别系统。     

神经网络与HMM构成的混合网络在语音识别中应用的研究

隐马尔可夫模型（ＨＭＭ）技术是语音识别中应用较为成功的算法，但它的缺点影响了其精度、速度、硬件实现和推广应用。神经网络（ＮＮ）具有并行性、强的分类能力和易于硬件实现等优点。将ＮＮ与ＨＭＭ相结合构成混合网络，能克服ＨＭＭ与ＮＮ的缺点，保留双方的优点。本文详细评述了目前在语音识别中应用的由ＨＭＭ和ＮＮ构成的四种混合网络。通过对其结构、识别性能和特点的分析，可以看出ＨＭＭ和ＮＮ构成的混合网的性能明显优于     

语音识别HMM中引入帧间相关信息的一种参数化模型

虽然隐马尔可夫模型（ＨＭＭ）是当前最为流行的语音识别模型，但由于一般都采用了状态输出独立假设，因此存在着不能描述语音现象中时间相关性的固有缺陷，本文提出的新模型对语音状态输出特征矢量序列的静态和动态特性信息分别进行参数化建模，然后将它们结合在一起，由此在基于段长分布的ＨＭＭ（ＤＤＢＨＭＭ）中引入了帧间相关信息，这种上引入帧间相关信息的ＨＭＭ能够更为精确地描述真实的语音现象。本文在给出新模型的框架后     

嵌入马尔可夫网络的多尺度判决融合耳语音情感识别

本文中我们提出了一种将高斯混合模型同马尔可夫网络结合的时域多尺度语音情感识别框架,并将其应用在耳语音情感识别中。针对连续语音信号的特点,分别在耳语音信号的短句尺度上和长句尺度上进行了基于高斯混合模型的情感识别。根据情绪的维度空间论,耳语音信号中的情感信息具有时间上的连续性,因此利用三阶的马尔可夫网络对多尺度的耳语音情感分析进行了上下文的情感依赖关系的建模。采用了一种弹簧模型来定义二维情感维度空间中的高阶形变,并且利用模糊熵评价将高斯混合模型的似然度转化为马尔可夫网络中的一阶能量。实验结果显示,本文提出的情感识别算法在连续耳语音数据上获得了较好的识别结果,对愤怒的识别率达到了64.3%。实验结果进一步显示,与正常音的研究结论不同,耳语音中的喜悦情感的识别相对困难,而愤怒与悲伤之间的区分度较高,与Cirillo等人进行的人耳听辨研究结果一致。      

语音帧间相关信息对基于HMM系统识别精度的影响

本文探讨经短时信号处理后的语音信号帧间相关信息对基于隐马尔可夫模型（ＨＭＭ）的语音识别系统识虽精度的影响，鉴于ＨＭＭ的输出独立假设导致语音帧间相关信息的损失，本文提出了一种描述帧间相关信息的统计模型－马尔可夫链（ＭＣＭ）用来弥补ＨＭＭ在这方面的缺陷；经非特定人和多话者孤立字实验表明，用ＭＣＭ作为ＨＭＭ的辅助模型，可将原有ＨＭＭ系统的识别率提高约１～６个百分点。     

基于电话用户交换机的语音识别系统研究

本论文对电话用户交换机研制了一个声控语音命令交换系统,该系统能够实现与特定人无关中小词汇量连续命令语音自动识别,研究中统计了用和命令语句,生成相应识别文法网络,识别系统的训练采用由子词模型构成的复合模型进行强化训练,识别采用令牌传递式改进Ｖｉｔｅｒｂｉ算法,提高系统的识别性能,论文比较了不同语音特征参数以及隐含马尔可夫模型状态数对电话语音识别精度的影响,研究中还开发识别系统拒识系统,在无拒识情况下     

语音识别隐马尔可夫模型的改进

由于在语音识别中被广泛应用的隐马尔可夫模型是一重马尔可夫模型，它不能充分地描述语音信号的时间相依性。虽然理论上可将ＨＭＭ扩展成多重马尔可夫模型，但由于所需运算量和存储量将成指数增长而使其难以应用。因此，本文提出一种新模型，它是由ＨＭＭ与一个能描述语音信号时间相依性的多维高斯密度函数相结合构成的。本文从理论上论证了新模型的合理性。对汉语不计声调的全部４０９个单音节的识别实验结果表明：新模型的识别率显     

Memory Access Optimized VLSI for 5000-Word Continuous Speech Recognition

We have developed a memory access reduced VLSI chip for 5,000 word speaker-independent continuous speech recognition. This chip employs a context-dependent HMM (hidden Markov model) based speech recognition algorithm, and contains parallel and pipelined hardware units for emission probability computation and Viterbi beam search. To maximize the performance, we adopted several memory access reduction techniques such as sub-vector clustering and multi-block processing for the emission probability computation. We also employed a custom DRAM controller for efficient access of consecutive data. Moreover, we analyzed the access pattern of data to minimize the internal SRAM size while maintaining high performance. The experimental results show that the implemented system performs speech recognition 2.4 and 1.8 times faster than real-time utilizing 32-bit DDR SDRAM and SDR SDRAM, respectively.     

基于HMM的连续小词量语音识别系统的研究

为了提高语音识别效率及对环境的依赖性,文章对语音识别算法部分和硬件部分做了分析与改进,采用ARMS3C2410微处理器作为主控制模块,采用UDA1314TS音频处理芯片作为语音识别模块,利用HMM声学模型及Viterbi算法进行模式训练和识别,设计了一种连续的、小词量的语音识别系统。实验证明,该语音识别系统具有较高的识别率和一定程度的鲁棒性,实验室识别率和室外识别率分别达到95.6%,92.3%。     

基于三轴传感器的老年人日常活动识别

本文针对老年人日常活动类型及特点提出了一种基于三轴加速度传感器和HMM（Hidden Markov Model）的活动识别方法.本文首先提取了针对老年人相异、相似活动的标准差、能量、相关系数、RAF（RAtio Forward）、RVF（Ratio Vertical Forward）等特征值.然后定义老年人的HMM活动识别模型.最后在经过Baum-Welch算法对HMM进行参数训练后使用Viterbi算法来进行老年人活动识别.实验结果表明,本文方法适用于老年人的日常活动的识别,平均识别精度达到了93.3%,尤其是对于相似步态活动的识别准确率达到了93.7%.     

基于经典隐马尔可夫模型的汉语连续语音识别系统

该文构造了基于经典隐马尔可夫模型(Hidden Markov Model,HMM)的汉语连续语音识别系统,定量地分析与评价了经典HMM的性能。     

The Hidden Markov Model of co-articulation and its application to the continuous speech recognition

The co-articulation is one of the main reasons that makes the speech recognition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend on the first-order assumption. In this paper, for modeling the co-articulation, a more perfect HMM than traditional first order HMM is proposed on the basis of the authors' previous works(1997, 1998) and they give a method in that this HMM is used in continuous speech recognition by means of multilayer perceptrons(MLP), i.e. the hybrid HMM/MLP method with triple MLP structure. The experimental result shows that this new hybrid HMM/MLP method decreases error rate in comparison with authors' previous works.     

Speech-to-Lip Movement Synthesis by Maximizing Audio-Visual Joint Probability Based on the EM Algorithm

In this paper, we investigate a Hidden Markov Model (HMM)-based method to drive a lip movement sequence with input speech. In a previous study, we have already investigated a mapping method based on the Viterbi decoding algorithm which converts an input speech signal to a lip movement sequence through the most likely HMM state sequence using audio HMMs. However, the method can result in errors due to incorrectly decoded HMM states. This paper proposes a method to re-estimate visual parameters using HMMs of audio-visual joint probability using the Expectation-Maximization (EM) algorithm. In the experiments, the proposed mapping method results in a 26% error reduction when compared to the Viterbi-based algorithm at incorrectly decoded bilabial consonants.     

基于HMM／VQ的认人的中等词表连续语音识别

本文讨论基于隐马尔可夫模型(HMM)和矢量量化(VQ)的连续语音识别方法。用这种方法,对每个单词作成一个HMM,对多个模型组合成的状态转移网络搜索其状态转移的最佳路径,从而实现不预先进行单词切分的连续语音的识别,使用有限态文法约束及其它一些改善识别性能的措施,演示系统能识别特定人的18种英语句式,150个单词,用312个话句(共有2710个单词)进行测试,识别延迟时间为发音时长的62％,发音速度平均为每秒2.32个单词,单词识准率为97.3％。     

Convergence of the maximum a posteriori path estimator in hiddenMarkov models

In a hidden Markov model (HMM) the underlying finite-state Markov chain cannot be observed directly but only by an additional process. We are interested in estimating the unknown path of the Markov chain. The most widely used estimator is the maximum a posteriori path estimator (MAP path estimator). It can be calculated effectively by the Viterbi (1967) algorithm as is, e.g., frequently done in the field of coding theory, correction of intersymbol interference, and speech recognition. We investigate (component-wise) convergence of the MAP path estimator. Convergence is shown under the condition of unbounded likelihood ratios. This condition is satisfied in the important case of HMMs with additive white Gaussian noise. We also prove convergence, if the Markov chain has two states. The so-called Viterbi paths are an important tool for obtaining these results     

Support Vector Machine Training for Improved Hidden Markov Modeling

We present a discriminative training algorithm, that uses support vector machines (SVMs), to improve the classification of discrete and continuous output probability hidden Markov models (HMMs). The algorithm uses a set of maximum-likelihood (ML) trained HMM models as a baseline system, and an SVM training scheme to rescore the results of the baseline HMMs. It turns out that the rescoring model can be represented as an unnormalized HMM. We describe two algorithms for training the unnormalized HMM models for both the discrete and continuous cases. One of the algorithms results in a single set of unnormalized HMMs that can be used in the standard recognition procedure (the Viterbi recognizer), as if they were plain HMMs. We use a toy problem and an isolated noisy digit recognition task to compare our new method to standard ML training. Our experiments show that SVM rescoring of hidden Markov models typically reduces the error rate significantly compared to standard ML training.