基于动态时间规整和神经网络的方言辨识研究

汉语方言辨识技术的研究不仅有利于提高方言语音识别系统的识别效率,而且对于公安部门的刑事侦查等方面都具有非常重要的应用价值。以湖南方言作为研究对象,对不同方言特征的差异及方言辨识中特征参量的合适选取进行了深入研究。针对语音信号具有很强的随机性而神经网络的输入结构相对固定等特点,提出了基于动态时间规整和神经网络的方言辨识方法。实验结果表明,选取相同的特征参数时对不同类别或不同声调的方言的辩识率不同。     

多信息融合的汉语方言辨识

文章提出了一种融合声学、音素配位和韵律特征等多信息融合的汉语方言辨识系统,分析了将语言信息转化为这些特征的实验方法,在此基础上,根据汉语方言辨识的特点,提出了一种基于概率模型的多信息辨识机制,实验结果表明,韵律特征对于短时语音具有很好的辨识效果,而音位配列特征对于长时语音更加有效。对于汉语三种方言的辨识,融合这三种特征的辨识率达95％。     

基于聚类支持矢量机的汉语方言辨识

该文提出了一种新的汉语方言辨识方法,来解决在总多辨识系统中存在的较弱辨识能力的问题,这种新方法运用高斯混合模型和N元语言模型,来产生一个全局的语言特征,然后使用聚类支持矢量机来做最后的分类。实验结果表明该方法不仅可以提高正确的辨识率,而且可以提高系统的鲁棒性。     

基于语音配列的汉语方言自动辨识

本文首先讨论了汉语方言辨识的依据及特征选取的基本原则,并由此导出了区间差分倒谱特征。然后利用GMM符号发生器和N元语言模型及ANN建立了一个方言辨识系统,该系统与传统的语种识别系统相比,具有以下特点:第一,系统不需要标注好的语音库,从而降低了汉语方言语音库建设的劳动强度和要求;第二, GMM符号化器计算量远远低于音素辨识器,从而提高了方言辨识速度,便于今后实时处理。第三,具有更高的辨识效果和更好的容错性。汉语普通话和三种方言辨识实验结果表明,系统平均辨识率可以达到83.8%。     

基于混合特征参数和BP_Adaboost的方言辨识

着眼于非特定人孤立词湖南地区的方言辨识,提出一种将BP神经网络和Adaboost算法相结合的辨识模型。为反映方言的动态特性及其声道特性,采用LPCC、MFCC和各自一阶差分系数相组合作为方言特征系数。利用多个BP神经网络作为弱分类器对方言进行初步辨识,借助Adaboost迭代算法将这些弱分类器组合起来构成强分类器,得出最终辨识结果。实验证明,该混合模型较单纯的BP神经网络具有更强的噪声鲁棒性和较高的识别率。     

关于朝鲜文信息技术标准化

信息技术标准是我国普及应用信息技术、弘扬民族文化、取得市场主动性的关键。该文分析了朝鲜语信息技术标准化国内外现状,论述了朝鲜语信息处理的必要性,并提出信息技术标准化工作的具体建议。该文认为统一的中国少数民族文字信息技术基础标准体系亟待完善,朝鲜语的信息技术标准化对我国朝鲜族文化的传承与发展具有深远意义,对形成系统、完整的中华语言文字信息处理统一平台、扩大国际影响、维护国家统一而言是不可或缺的工作。
     

基于高斯混合模型的汉语方言辨识系统

建立了一个基于高斯混合模型的汉语方言辨识系统,并给出了模型参数的估计方法,讨论了特征参数和高斯混合数对系统辨识的影响,实验结果表明,系统对同一省内的三种不同方言的辨识率平均可以达到84.17%。     

基于滑动倒谱的自动语言辨识

滑动差分倒谱在自动语言辨识的研究中获得了广泛的应用. 但是滑动差分倒谱并没有利用语音信号的静态倒谱信息,在方言辨识中的研究表明静态倒谱比差分倒谱含有更多的特征信息. 为此,提出了滑动倒谱( SC)的概念, 并与滑动差分倒谱特征矢量进行了对比研究. 首先利用开发集的语音考察了滑动差分倒谱和滑动倒谱的控制参数在不同取值的情况下对识别性能的影响,利用爬山法确定了这2类特征矢量达到局部最优控制参数组合的路径,然后利用测试集的数据对优化后的2类特征矢量建立的模型进行了闭集辨识和开集辨识. 2种情况下的测试结果都表明滑动倒谱的性能优于滑动差分倒谱. 并且这2种参数还具有特征互补性,将它们进行决策级数据融合可以进一步提高系统的性能.     

基于差分特征和高斯混合模型的湖南方言识别

语音的韵律是区分汉语方言的重要语音声学特征,而语音的差分特征是语音韵律的重要体现。采用差分特征ΔMFCC和ΔΔMFCC作为特征参数,用高斯混合模型（GMM）作为训练模型,通过计算测试样本的似然概率来识别方言的类型。用该方法对长沙方言、邵阳方言、衡阳方言和普通话进行了识别研究,并与采用MFCC作为特征参数的识别效果进行了比较。实验结果表明差分特征具有识别率高、抗噪声性能更好等优点。     

全局信息融合的汉语方言自动辨识

提出身份认证矢量（Identity vector,I-vector）结合韵律信息的汉语方言辨识方法。全差异空间替代本征音与本征信道空间,将高维超矢量映射为低维I-vector表示,并进行信道补偿与特征降维处理。汉语是有调语言,各方言在其韵律结构上具有明显差异,I-vector特征融合全局韵律信息,可有效增补各方言鉴别性。利用融合信息对闽、粤、吴等五种方言以及普通话进行辨识实验,等错率（Equal Error Rate,EER）达到8.01%,比高斯混合模型-通用背景模型（Gaussian Mixture Model-Universal Background Model,GMM-UBM）降低56.2%,表明融合全局韵律信息的I-vector方法可有效提高汉语方言辨识正确率。     

一种新的低俗语音识别方法

为了应对低俗视频语音等多媒体信息在网络上的大量传播,提出了一种基于移位差分倒谱参数特征的低俗语音识别方法。该方法对输入的语音信号进行分帧,提取移位差分倒谱参数特征,采用了高斯混合模型进行粗分类,对粗分为低俗的语音帧再用支持向量机分类器进行确认。实验结果表明,该方法具有较高的正识别率和较低的误识别率,可用于网络上低俗语音和视频信息的过滤。     

EMD-SDC方法在机载连接词语音识别系统中的应用

机载连接词语音识别系统与传统语音识别系统相比,具有背景噪声大,系统识别率要求高等特点。依据这些特点,提出了一种基于经验模态分解增强和位移差分倒谱特征的EMD-SDC连接词语音识别方法。经验模态分解的调频调幅特性,可以有效提高机载复杂噪声背景下的端点检测准确度,位移差分倒谱特征由语音帧的一阶差分谱连接扩展而成,能够更好地提取依赖于语言结构的时序信息。该方法对机载交通预警避撞系统提示语音库进行测试,实验结果表明,采用EMD-SDC方法的机载连接词语音识别系统,能够很好地克服机舱背景噪声干扰,在低信噪比条件下实现较高的识别率。     

Off-line handwritten Korean character recognition based on stroke extraction and representation

In this paper, we propose an off-line recognition method for handwritten Korean characters based on stroke extraction and representation. To recognize handwritten Korean characters, it is required to extract strokes and stroke sequence to describe an input of two-dimensional character as one-dimensional representation. We define 28 primitive strokes to represent characters and introduce 300 stroke separation rules to extract proper strokes from Korean characters. To find a stroke sequence, we use stroke code and stroke relationship between consecutive strokes. The input characters are recognized by using character recognition trees. The proposed method has been tested for the most frequently used 1000 characters by 400 different writers and showed recognition rate of 94.3%.     

Character recognition based on attribute-dependent programmedgrammar

The recognition of Korean characters by a syntactic method is considered. Korean characters are composed of phonetic symbols in two dimensions and contain very little redundancy. In addition, the phonetic symbols in each character are different in shape and number depending on how they are composed. Thus, attribute information is important. A Korean character recognition algorithm based on an attribute-dependent programmed grammar is presented. The preprocessing and primitive extraction algorithm is also described. The algorithm was implemented and tested with more than 9600 Korean characters in pages randomly selected from children's story books. The algorithm based on the attribute-dependent programmed grammar recognized characters reasonably quickly, with more than 95.1% accuracy     

基于SDC特征和GMM-UBM模型的自动语种识别*

本文提出了一种基于SDC特征和GMM-UBM模型的自动语种识别方法。SDC特征由许多语音帧的一阶差分谱连接扩展而成,与传统的MFCC特征相比,包含了更多的时序特征信息。UBM模型反映了所有待识别语种的特征分布特性,借助贝叶斯自适应算法可以快速得到每个语种的模型。与传统的GMM方法相比,该方法的训练和识别的速度更快。该方法对OGI电话语音库中11个语种进行了测试,其10秒、30秒和45秒句子的最佳识别正确率分别为72.38%、82.62%和85.23%,识别速度约为0.03倍实时。     

On-line recognition of Korean characters using ART neural network and hidden Markov model

This paper proposes an efficient method for on-line recognition of cursive Korean characters. The recognition of cursive strokes and the representation of a large character set are important determinants in the recognition rate of Korean characters. To deal with cursive strokes, we classify them automatically by using an ART-2 neural network. This neural network has the advantage of assembling similar patterns together to form classes in a self-organized manner. To deal with the large character set, we construct a character recognition model by using the hidden Markov model (HMM), which has the advantages of providing an explicit representation of time-varying vector sequence and probabilistic interpretation. Probabilistic parameters of the HMM are initialized using the combination rule for Korean characters and a set of primitive strokes that are classified by the ART stroke classifier, and trained with sample data. This is an efficient means of representing all the 11,172 possible Korean characters. We tested the model on 7500 on-line cursive Korean characters and it proved to perform well in recognition rate and speed.     

Static and dynamic information derived from source and system features for person recognition from humming

In this paper, hum of a person (instead of normal speech) is used to design a voice biometric system for person recognition. In addition, a recently proposed static feature set, viz., Variable length Teager energy based Mel Frequency Cepstral Coefficients (VTMFCC), is found to capture source-like information of a hum signal. Effectiveness of VTMFCC over linear prediction (LP) residual to capture the complementary information than MFCC is demonstrated in a hum signal. Person recognition performance is found to be better when a score-level fusion is used by combining evidences from static and dynamic features for MFCC (system) and VTMFCC (source-like) features than MFCC alone. Experiments are validated on two types of dynamic features, viz., delta cepstrum and shifted delta cepstrum. In addition, for score-level fusion using static and dynamic features % identification rate and % Equal Error Rate are observed to outperform by 7.9?% and 0.27?%, respectively than MFCC alone. Furthermore, we have observed that person recognition system gives better performance for larger frame duration 69.6?ms as opposed to traditional 10–30?ms frame duration.     

A method of recognition and representation of korean characters by tree grammars

A syntactic method is applied to the recognition of Korean characters (Hangul). Since they develop into complex characters by the sequential addition of fundamental characters under positioning rules, there are a large amount of characters and consequently there exist many similar characters. Therefore, the sequential extraction, according to the positioning rules, of fundamental characters composing Korean characters is effective for automatic recognition. As a structural analysis, a production process of fundamental characters is represented by tree grammars, and the extraction algorithm of fundamental characters and the results of computer simulation are described.     

A dynamic gesture recognition system for the Korean sign language(KSL)

The sign language is a method of communication for the deaf-mute. Articulated gestures and postures of hands and fingers are commonly used for the sign language. This paper presents a system which recognizes the Korean sign language (KSL) and translates into a normal Korean text. A pair of data-gloves are used as the sensing device for detecting motions of hands and fingers. For efficient recognition of gestures and postures, a technique of efficient classification of motions is proposed and a fuzzy min-max neural network is adopted for on-line pattern recognition.