利用线性预测谱LPC对元音区别力量化分析的研究

本研究利用LPC对10位发音人的正常单元音相同声调（a、o、e、i、u、ü）进行识别测试,进一步探讨LPC提取出来的各个参数对于区分说话人的作用。提取元音最平稳的一段进行长时LPC分析,分析不同人的语声声纹差异性和同一人语声声纹的总体特殊性。结果显示,每个话者的自身差异都明显小于话者之间的差异。因此利用LPC提取元音的共振峰振幅与相邻弱谷幅值之差对比分析对话者具有有效区别力。     

女性普通话塞音过渡音征个体特性初探

目的考察塞音过渡音征的个体特性及在说话人鉴定中的价值。方法选取9位女性发音人普通话中的6个塞音与元音/i、a、u/组成的单音节,提取每个音节F2、F3的起点值和目标值进行统计分析,并计算说话人的塞音音轨。结果 （1）过渡音征形态特征在不同说话人之间具有差异;（2）各音节的说话人区分率呈现较大区别,音节/tu/的说话人区分率较高而/khu/音节几乎不具备说话人区分能力;（3）与零声母音节相比,音节中3个元音的F2共振峰频率均值受到塞音的影响而提高,其中/i、a/F2提高的幅度要大于/u/;（4）不同说话人的音轨存在差异。结论在说话人鉴定中选取塞音音节进行比对时要注意不同音节的说话人区分率,尽量避免选取舌根塞音音节;塞音过渡音征的形态和音轨数据可以应用于说话人鉴定。     

正常、大声两种说话状态下语音的声学差异及对声纹鉴定的影响

本文主要通过对正常、大声两种说话状态下的普通话中三个单元音[a]、[i]、[u]的声强、时长、基频、谐波振幅差值、共振峰等声学参数的分析,综合比较了各参数的变化规律,发现大声说话时的语音并非正常语音的简单放大,二者不仅在声强上存在差别,同时在频率域上也发生了重要变化。同一人不同状态下发音的频谱特征差异性较大,同种状态下发音的相似性、可比性较强,为此,声纹鉴定中应尽量选取状态相同的语音进行比对。     

正常、大声两种说话状态下语音的声学差异及对声纹鉴定的影响

本文主要通过对正常、大声两种说话状态下的普通话中三个单元音[a]、[i]、[u]的声强、时长、基频、谐波振幅差值、共振峰等声学参数的分析,综合比较了各参数的变化规律,发现大声说话时的语音并非正常语音的简单放大,二者不仅在声强上存在差别,同时在频率域上也发生了重要变化。同一人不同状态下发音的频谱特征差异性较大,同种状态下发音的相似性、可比性较强,为此,声纹鉴定中应尽量选取状态相同的语音进行比对。     

不同频率共振峰在话者识别中的鉴别价值

目的研究在话者识别领域,不同频率共振峰特征价值的大小。方法对10对女性与8对男性双胞胎正常朗读语音的共振峰频率特性进行定量测量、比较、分析,统计。结果男性和女性双胞胎个体依据2000Hz以下、2000-5000Hz、5001-8000Hz不同频率范围内的共振峰均可区分,但共振峰的缺峰比例随着频率的升高而升高,5001-8000Hz范围的缺峰比例达26.67%。结论不同频率共振峰在话者识别中的区别能力无显著差异。     

声纹鉴定中普通话音素间过渡方式特征研究

不同人所讲的普通话语流中相邻音素间的过渡方式分为不同的类型。音节内辅音-元音之间、音节间元音-辅音之间的过渡方式分为清晰过渡(或停顿过渡)和模糊过渡(或缓冲过渡)两种类型;音节内元音-辅音之间的过渡方式分为间断过渡和连续过渡两种类型;音节内元音-元音之间的过渡方式分为平滑过渡、间断过渡、交错过渡和异变过渡四种类型。对同一人的发音而言,不论其相邻音素间的过渡方式属于上述哪种类型,都表现出较强的自身同一性。因此音素间的过渡方式可以作为声纹鉴定中的一类特征。     

白噪声不同信噪比对语音基音和共振峰的影响研究

目的研究不同强度白噪声对语音特征提取的影响,总结变化规律,为带噪语音的声纹鉴定提供参考。方法对TIMIT连续语音语料库中的录音样本加载不同强度白噪声,使用语音工作站提取纯净语音、不同信噪比带噪语音的基频、共振峰,研究分析白噪声对语音特征参数的影响。结果低噪环境下,语音共振峰相对稳定,增大噪声强度,共振峰出现偏移或者无法检出现象;各阶共振峰抗噪能力不同,低阶共振峰抗噪声能力强,稳定度高,高阶共振峰抗噪能力弱,稳定性差,低阶共振峰抗噪能力优于高阶共振峰;基音在各种噪声强度下稳定度高,具备较强鲁棒性。结论信噪比降低会引起共振峰频率偏移,甚至丢失共振峰;噪声对高阶共振峰影响大于低阶共振峰;基频在噪声环境下具备较高的抗干扰能力,声纹鉴定中应重点分析噪声对语音特征的影响。     

基于语料库的“普通话”地域性言语识别技术

目的探究汉语＂普通话＂中的地域性差别,发现言语特征,找到从有限的以普通话发音的语音材料中提取出更多地域性特征的途径和方法,提高地域性言语识别技术水平,更有效地为案件分析定向服务。方法在建立较大规模的《面向案件言语识别应用的汉语＂普通话＂语料库》及查询检索系统的基础上,进行统计分析、归纳总结。结果人们说普通话时会在声母、韵母、声调、重音、儿化、轻声等语音方面和词汇、语法等方面不同程度地出现其母语方言的固有特点。我们可以采用＂以调值特征为中心,声韵特征相结合＂、＂利用各类特征的总和进行综合评断＂等方法进行识别。结论利用＂普通话＂语声进行言语人地域性识别是一种切实可行的技术方法。     

利用FT-IR检验纸张初探

目的初步探讨利用傅立叶红外光谱仪对纸张检验的鉴别力。方法利用傅立叶红外光谱仪对不同种类纸张、同一厂家不同批次的纸张进行检验。结果通过比较红外光谱图中出现的特征峰差异,确定纸张的差异。结论用该方法可以对不同种类纸张、同一厂家不同批次的纸张进行区分,同时可以分析纸张中有机物的特征基团。     

似然比在法庭说话人确认中的应用

本文把成功应用于DNA检验的证据评估方法（似然比）应用于法庭语音证据评估之中,提取语音的LPC作为识别特征,并使用45人电话对话录音中元音/a/作为样本进行了测试。结果表明该方法不仅能正确识别说话人,而且能根据当前嫌疑人样本和问题语音样本的差异,量化该语音样本作为证据的力度,为法庭提供科学合理的证据评估结果和科学解释。同时,自动特征提取的引入比起人工提取共振峰特征,提高了工作效率,识别系统性能也获得大幅提升。     

A test of the effectiveness of speaker verification for differentiating between identical twins

This paper presents investigations into the ability of speaker verification technology to discriminate between identical twins. It is shown that whilst, in general, the genetic and non-genetic characteristics of voice are both of value to speaker verification capabilities, it is the latter which is highly beneficial in the separation of the speech of identical twins. It is further demonstrated that through the use of unconstrained cohort normalisation as a complementary means for the exploitation of such voice characteristics, the verification reliability can be considerably enhanced for both identical twins and unrelated speakers. Experiments were conducted using a bespoke clean-speech database consisting of utterances from 49 identical twin pairs. The paper details the problem in speaker verification posed by identical twins, discusses the experimental investigations and provides an analysis of the results.     

Production of intoxication states by actors--acoustic and temporal characteristics

This paper is the second of a series; the first has been published (J Forensic Sci, 1998;43:1153-62). The goal in the initial pair of experiments was to determine if speakers (actors) could effectively mimic the speech of intoxicated individuals and also volitionally reduce the degradation to their speech that resulted from severe inebriation. To this end, two highly controlled experiments involving 12 actor-speakers were carried out. It was found that, even when sober, nearly all of them were judged drunker (when pretending) than when they actually were severely intoxicated. In the second experiment, they tried to sound sober when highly intoxicated; here most were judged less inebriated than they were. The goal of this second paper is to identify some of the speech characteristics that allowed the subjects to achieve the cited illusions. The focus here is on four paralinguistic factors: fundamental frequency (F0), speaking rate, vocal intensity, and nonfluency level. For the simulation of intoxication study, it was found that F0 was raised along with increased intoxication but raised even more when this state was feigned. A slowing of speaking rate was associated with increasing intoxication, but this shift also was greater when the speaker simulated intoxication. The most striking contrast was found for the nonfluencies; they were doubled for actual intoxication, but quadrupled when intoxication was simulated. On the other hand, the shifts exhibited by the subjects when they attempted to sound sober were not as clear cut. Indeed, no systematic relationships were found here for either F0 or vocal intensity. Both speaking rate and the number of nonfluencies shifted appropriately, but these changes were not statistically significant. In sum, discernable suprasegmental relationships occurred for both studies (but especially the first); further, it is predicted that useful cues also will be found embedded in the segmentals (the sounds of speech).     

Intra- and inter-speaker variations of formant pattern for lateral syllables in Standard Chinese

Speech variation of speakers is a crucial issue for speaker recognition and identification, especially for forensic practice. Greater intra-speaker variation is one main reason for incorrect speaker identification in real forensic situations. Understanding the stability of acoustic parameters and their variation in speech is therefore significant for the evaluation of effective parameters for speaker identification. In this paper, all vowels in Standard Chinese including five monophthongs, eight diphthongs and four triphthongs were combined with lateral /l/. Finally, 15 lateral syllables with different tones for 10 speakers were selected and acoustically analyzed. Central frequencies of the first four formants for each syllable were measured for quantitative comparison of intra- and inter-speaker variation in order to provide a general idea of speaker variation in Standard Chinese, and finally serving for forensic application. Results show that the overall intra-speaker variation is less than the inter-speaker variation in great extent under laboratory condition though occasionally they are contrary. This supports the basis for forensic speaker identification, that is, intra-speaker variation should be less than inter-speaker variation in many acoustic features, and further validates the probability and reliability of forensic speaker identification.     

Proposing Problem-Based Learning for teaching future forensic speech scientists

In the last 10–15 years, Masters programmes and undergraduate modules have emerged in the UK that teach forensic speech science. Forensic speech science is the forensic subdiscipline concerned with analysing speech recordings, such as telephone calls of unknown speakers, when they arise as evidence. In order to answer questions surrounding the identity of the speakers in these recordings, forensic speech analysts draw on their expertise in phonetics and acoustics. Even though existing UK forensic speech science programmes do not claim to train students to a level where they are in a position to carry out real-life forensic casework, a proportion of the graduates from these programmes do go on to fill discipline-specific roles in security organisations or for private providers of forensic speech analysis. It is therefore surely in the community’s interests to review educational approaches to capitalise on the current training opportunities. This paper specifically proposes to explore the potential of a Problem-Based Learning (PBL) approach to forensic speech science teaching. PBL is a student-centred learning approach that heavily relies on the students’ independence in the solving of ill-structured problems. PBL has shown to be beneficial to programmes that directly lead on to discipline-specific professional roles, and has even become the standardised teaching approach in some of those areas (medicine being the flagship example). Given its reported success in other disciplines, the question arises as to whether PBL could bring similar benefits to prospective forensic speech practitioners and to forensic speech science as a whole.     

降噪处理及其对语音的影响

司法声学中有两种导向的降噪处理模式：一是在语音内容辨听鉴定中。通过降噪处理，减弱噪声的掩蔽效应。提高语音听觉的清晰度和可懂度：另一种是在说话人鉴定中，通过降噪处理，减弱噪声对语音声学特征的干扰。使语图更为清晰可辨。本实验中。录制了日常生活中经常遇到的20余种噪声。通过混音，对每一个噪声合成出四个等级信噪比的含噪语音声样。然后，利用STC降噪系统、Adobe Audition软件和VS6．0语音工作站，分别对含噪语音进行降噪处理。实验发现。经过降噪处理，多数声样的噪声掩蔽效应能够减弱．部分声样的宽带语图得到改善。最后讨论了降噪处理对语音的影响及利用降噪语音进行说话人鉴定的注意事项。     

Forensic reference data on articulation rate in German.

Articulation rate (AR) is one of the parameters used in forensic voice comparisons for the purpose of providing evidence for or against speaker identity, yet at present multi-speaker studies on this parameter are very rare. In order to alleviate this situation AR was measured in the speech of 100 German-speaking male subjects. Histograms were provided from which the forensic expert can infer the percentages of different AR values in the population. Separate histograms were provided for mean AR and standard deviation of AR. It was also found that mean AR is significantly higher in read than spontaneous speech and that AR standard deviation is significantly smaller in read than spontaneous speech, although many individual speakers deviate from this general pattern.     

Language Proficiency and Police Officers’ Lie Detection Performance

We examined lay persons’ and police officers’ abilities to detect lying in second-language speakers. Participants (N?=?121) viewed targets who were lying or telling the truth about an event in either their first or second languages. Overall, participants were better able to detect deception in native-language speakers than second-language speakers. In addition, they tended to believe that native-language speakers were telling the truth. However, contrary to our hypotheses, expertise did not affect lie detection performance. Implications will be discussed.     

Anonymous Speakers and Confidential Sources: Using Shield Laws When They Overlap Online

The development of the Internet as a mass medium has created new tensions between the rights to speak anonymously and to be protected against defamation. Some courts have developed balancing tests to determine when anonymous speakers should be unmasked, the most popular of which generally require some initial showing of prima facie evidence. Other times, shield laws have been used to protect the anonymous when comments have been posted on news organization Web sites. However, news organizations should be cautious when using shield laws to protect anonymity, and judges should evaluate privilege claims as they always have. In other instances, anonymity appears to be adequately protected by summary judgment balancing tests. An approach in which news organizations focus on the type of comment and its potential journalistic contribution in deciding how to protect commenters’ identities could help ensure that anonymous speech is properly protected without harming shield laws.