人机语言通讯的新进展──Eurospeech’97及其卫星会

本文以介绍第五届欧洲言语通讯和技会议－Ｅｕｒｏｓｐｅｅｃｈ’９７及其卫星会议为主，概述言语科学与技术研究领域的国际学术会议情况以及本领域的最新发展。     

汉语耳语音孤立字识别研究

耳语音识别有着广泛的应用前景,是一个全新的课题.但是由于耳语音本身的特点,如声级低、没有基频等,给耳语音识别研究带来了困难.本文根据耳语音信号发音模型,结合耳语音的声学特性,建立了一个汉语耳语音孤立字识别系统.由于耳语音信噪比低,必须对其进行语音增强处理,同时在识别系统中应用声调信息提高了识别性能.实验结果说明了MFCC结合幅值包络可作为汉语耳语音自动识别的特征参数,在小字库内用HMM模型识别得出的识别率为90.4%.     

The Effects of a Specific Speech and Language Training Program on Students of a Radio Announcing Course

The purpose of this study was to determine whether individuals show differences in speech and voice during reading of the same news before and after attending a radio announcing course. Twenty-five students of a Radio Announcing Course in Sao Paulo city, 17 men and 8 women, aged 19 to 55 years, participated in this study. The readings were recorded in a professional audio studio, and the speech samples were submitted to perceptual and acoustic analysis. For the perceptual analysis, the samples were randomly presented in pairs and five trained speech pathologists identified each recording as pre- and posttraining, and also justified their choices by indicating what parameters better based their judgment: type of voice, articulation and pronunciation, loudness, pitch, resonance, speech rate, respiratory coordination, and use of emphasis. The acoustic parameters analyzed were mean, minimum, and maximum fundamental frequency, frequency range, text duration, and pause duration. The perceptual analysis showed that the posttraining speech samples were considered the best productions in 80% of the evaluations. Emphasis characterized the readings (70.4%), followed by type of voice (44.8%) and pitch (40.8%). Acoustic analysis showed higher mean fundamental frequency and increase of frequency range posttraining. These results indicated richer modulation in the posttraining readings. There are differences in the readings of the same news pre- and posttraining in a radio announcing course, and the posttraining reading was considered the best production, indicating the positive effect of the training.     

Study on the method and system implementation of an isolated word recognition system used in noisy environment

I.IntroductionRecentlytherearemanykindsofsystemsandproductsforspeechrecognition,butalmostallofthemareworkinginquietenvironment,theperformancearedegradedorevencan'tworkwhenitisoperatedinhighnoisyenvironmentssuchasincockpits,vehicle,workshopsetc.SonoiserobustnesshasbecomeoneofthemainobstaclesfortherealaPplicationsoftheautomaticspeechrecognizersanditattractstheattentionofresearchersinspeechtechnologyareas.Since1978,substantialeffortshavebeendevotedtotestandevaluatethespeechrecognizersusedinfight…     

Sound modes in composite incommensurate crystals

We propose a simple phenomenological model describing composite crystals, constructed from two parallel sets of periodic inter-penetrating chains. In the harmonic approximation and neglecting thermal fluctuations we find the eigenmodes of the system. It is shown that at high frequencies there are two longitudinal sound modes with standard attenuation, while in the low frequency region there is one propagating sound mode and an over-damped phase mode. The crossover between these two regions is analyzed numerically and the dynamical structure factor is calculated. It is shown that the qualitative features of the experimentally observed spectra can be consistently described by our model. Received 28 November 2001 and Received in final form 23 January 2002     

实时识别中语音的时域─频域─能量表示

本文提出了语音信号的一种时域－频域－能量表示,并给出了算法,可用于孤立词语音识别,这种时域－频域－能量表示有两个特点,基于短时能量梯度的非线性时间规正,可保留语音信号频域的过滤特性,丢掉其稳态特性,计算量小,适于实时应用。     

Recognition of Putonghua voiceless stop like initials based on speech main periods

I.Intr0ductionNowadays,thereismuchadvancemcntinthcrcsearchintospeechrecognition.Manyresearchershavebecninterestedintheimplementationofareliab1crealtimerec-ognitionsystemofunlimitedv0cabu1ary.Thercareafewproductsconversingsyl1ablesintoChinesecharactersinthemarket.However,theimp1ementationofarobustrealtAnerecognitionsystemofunlimitcdvocabularyisvcrydifficu1t,anditisthcgreataimofourresearch.WehaveaTMS32O-C25signa1processingboardattachedtoacomputerofthM-PC/AT80386.Wehopcthatourspeechrecognit…     

Sound Signal Based Fault Classification System in Motorcycles Using Hybrid Feature Sets and Extreme Learning Machine Classifiers

Vehicles generate dissimilar sound patterns under different working environments. These generated sound patterns signify the condition of the engines, which in turn is used for diagnosing various faults. In this paper, the sound signals produced by motorcycles are analyzed to locate various faults. The important attributes are extracted from the generated sound signals based on time, frequency and wavelet domains which clearly describe the statistical behavior of the signals. Further, various types of faults are classified using the Extreme Learning Machine (ELM) classifier from the extracted features. Moreover, the improved classification performance is obtained by the combination of feature sets in different domains. The simulation results clearly demonstrate that the proposed hybrid feature set together with the ELM classifier gives more promising results with higher classification accuracy when compared with the other conventional methods.     

硫酸卡那霉素颜色的谱识别方法

本文提出一种硫酸卡那霉素药液颜色的谱识别新方法。该方法突破了传统的三刺激值测色模式，提出了用光谱特征及非固定的背景模式代替三刺激值及ＣＩＥ测量模式，建立了良好的判别函数，适于药液颜色的客观检测与定级，结果令人满意     

基于离散极大值法的太赫兹光谱特征吸收峰提取方法

太赫兹波在电磁波谱中介于微波和红外辐射之间,具有指纹特性、安全无损、强穿透性等特点,因此太赫兹光谱技术在药品成分和组成检测领域具有广泛应用价值。针对高纯度物质识别研究中存在部分弱吸收峰不易识别,以及混合物的太赫兹光谱中吸收峰强度降低而导致吸收峰位信息模糊化的问题,提出了一种基于离散极大值法的光谱吸收峰位识别方法,即伴随拐点法。伴随拐点法首先利用目标检测物太赫兹吸收系数谱图的一阶和二阶导数确定吸收峰位的伴随拐点和基线谱,其次将原始吸收光谱与基线谱进行差分运算得到差谱,最后根据离散极大值法确定吸收峰位,从而实现特征吸收峰的识别。为验证伴随拐点法的有效性,采用伴随拐点法对四种硝基呋喃类样品光谱进行吸收峰提取,并将吸收峰位识别结果与仿真结果进行比较。实验结果证明,伴随拐点法能有效识别目标检测物的强吸收峰和弱吸收峰。该方法不仅在含峰目标物的太赫兹特征吸收峰识别问题中具有广泛的应用前景,还适用于其他光谱的谱峰峰位检测。     

MPEG-2先进音频编码(AAC)的研究和软件仿真

ＭＰＥＧ－２ＡＡＣ是ＩＳＯ／ＩＥＣ ＭＰＥＧ组织继 ＭＰＥＧ－１、ＭＰＥＧ－２音频编解码标准后,制定 的最新国际标准（ＩＳＯ／ＩＥＣ １３８１８－７）,在６４ｋｂｐｓ／每声道低码率时能提供全透明音质。本文对其编 解码算法进行了简要介绍。论文作者对ＭＰＥＧ－２ＡＡＣ进行了软件仿真,文中介绍了仿真结果,仿 真时对ＡＡＣ标准所附编码范例中的一些不妥之处,作了改进,文中列举了６方面的修正。     

语言声学的进展

本文涉及语言声学的语音学研究、文语转换技术、语音识别技术及自然语言处理等方面，简要介绍了有关汉语在前三方面的进展和发展方向；重点介绍了面向整个自然语言理解处理的新理论一概念层次网络（HNC）理论的主要内容及其进展，试图在理论层面上给出HNC理论的基本概貌。     

Experimental Realization of Perfect Discrimination for Two Unitary Operations

We experimentally demonstrate perfect discrimination between two unitary operations by using the sequential scheme proposed by Duan et al.[Phys. Rev. Lett. 98 (2007) 100503] Also, we show how to understand the scheme and to calculate the parameters for two-dimensional operations in the picture of the Bloch sphere.     

近红外漫反射光谱法快速无损鉴别阿胶真伪

采用近红外光谱漫反射光谱技术和模式识别技术快速鉴别阿胶真伪.收集来源不同的阿胶(真品8个,伪品6个),采集其近红外漫反射光谱,使用多重散射校正和小波变换对光谱进行预处理后,分别应用相似度匹配和马氏距离方法建立质量鉴别模型.相似度法使用真品谱图作为标准谱图,用样品谱图与标准谱图的相似度值来鉴别阿胶质量;对阿胶样品进行重复扫描得到28张谱图,随机分为3组后应用马氏距离法建立交叉验证鉴别模型.两种模式识别方法均能准确无误的鉴别阿胶真伪,表明近红外光谱和模式识别技术结合可快速、准确、客观地进行阿胶质量鉴别,可推广到其他中成药的质量鉴别.     

MPEG-2先进音频编码(AAC)的研究和软件仿真

ＭＰＥＧ－２３ＡＡＣ是ＩＳＯ／ＩＥＣＭＰＥＧ组织继ＭＰＥＧ－１,ＭＰＥＧ－２音频编解码标准后,制定的最新国际标准（ＩＳＯ／ＩＥＣ１３８１８－７）在６４ｋｂｐｓ／每声道低码率时能提供全透明音质,本文对其编解码算法进行了简要介绍,论文作者对ＭＰＥＧ－２ＡＡＣ进行了软件仿真,文中介绍了仿真结果,仿真时对ＡＡＣ标准所附编码范 中的一些不妥之处,作了改进,文中列举了６方面的修正。     

四种黑檀心材的红外光谱差异化与聚类分析

利用红外光谱结合模式识别和二维相关光谱对乌木、东非黑黄檀、风车木和成对古夷苏木四种黑檀硬木心材进行鉴别和聚类分析。红外光谱显示四种木材中的主体成分为纤维素（特征吸收峰位置在~1 370, ~1 158, ~1 034和~895 cm-1附近）、木质素（特征吸收峰位置~2 935, ~1 510, ~1 462和~1 426 cm-1附近）和草酸钙（特征吸收峰位置~1 615, ~1 318和~781 cm-1附近）。三种主体成分在四种木材红外光谱之间的相对峰强度H表明：乌木和东非黑黄檀中木质素含量较高,风车木中草酸钙含量较高,成对古夷苏木中含有一定量的脂类成分。根据红外光谱的差异性选取不同的波段,优选计算参数,分别对四种硬木心材进行相关系数判别分类和SIMCA聚类分析。相关系数判别分类模式识别中,成对古夷苏木中有一个样本未得到有效的验证,但是其余三个木材样品均得到了有效验证。SIMCA聚类模式识别中,四种木材心材之间的识别率、拒绝率和验证率都达到100%,说明不同木材之间没有重叠区域,可以完全的区分识别。二维相关红外光谱中,乌木与东非黑黄檀在升温过程中纤维素的C—O和C—C基团对温度敏感性较高,风车木中草酸钙热敏性较高,成对古夷苏木中木质素的热敏性高于纤维素。红外光谱结合聚类分析和二维相关红外光谱,不仅可以对木材主体成分进行的定性和相对含量的分析,在完善聚类模型基础上还可以对木材种类进行快速、有效的分类模式识别。     

激光诱导击穿光谱的自组织特征映射结合相关判别对天然地质样品分类方法研究

激光诱导击穿光谱技术具有微损、原位、快速分析的特点,在样品分类识别、成分分析等领域有广阔的应用前景。为探索该技术在天然地质样品识别应用的可行性,提出了一种自组织特征映射神经网络结合相关判别对天然地质样品LIBS光谱分类识别的方法。为减小全谱中背景噪声等不相关数据干扰、降低计算量,在元素谱线归属的基础上进行了特征谱线提取,实现了高维光谱数据的降维。以特征谱数据为输入建立网络训练模型,得到具有输入样本特征的权向量,通过权向量与待测样本进行相关分析可以实现样品分类。对16种天然地质样品的分类算法实验证明,在全谱、主成分降维和特征谱段三种数据处理方法中,特征谱的降维和提取LIBS数据主特征效果最优。改进的SOM网络结合相关判别算法比支持向量机方法和直接应用SOM网络方法的分类准确度更高,初步证实了该方法的有效性。