伪装语音的自动话者识别研究

本文以语音自动话者识别系统为平台,对实际案件中出现频率较高的10种伪装语音类型进行自动话者识别测试。通过对20位发音人的正常语音和10种类型伪装语音的话者辨认和话者确认测试,分析不同语音伪装类型对自动话者识别的影响。该结果对于深入认识伪装语音的特性及其话者识别研究具有重要意义,也为自动话者识别技术的改进提供了参考。     

电子伪装语音的变声规律研究

本文以目前社会上流行的两款不同类别的电子伪装语音器材为对象,对多名实验对象变声前、后的声学特征（基频、共振峰、声调、能量和过零率等）进行了深入的实验分析。实验结果和分析表明,变声相对于原声,其声学特征变化是有规律的,根据这一声学特征变化规律,对变声语音逆变声就能得到与原声符合很好的恢复语音,这为深入开展对经过电子伪装的语音进行同一人鉴定奠定了基础。     

电子伪装语音的变声规律研究

本文以目前社会上流行的两款不同类别的电子伪装语音器材为对象,对多名实验对象变声前、后的声学特征(基频、共振峰、声调、能量和过零率等)进行了深入的实验分析。实验结果和分析表明,变声相对于原声,其声学特征变化是有规律的,根据这一声学特征变化规律,对变声语音逆变声就能得到与原声符合很好的恢复语音,这为深入开展对经过电子伪装的语音进行同一人鉴定奠定了基础。     

语音身份识别及其在犯罪侦查中的运用

语音身份识别是通过说话人的语音分析其性别、年龄、职业、文化程度等,从而推断说话人身份的一种人身识别技术。语音身份识别一般需通过听辨和视图检测,有的还需聘请专家会检。语音身份识别在刑事犯罪中可以确定侦查方向、缩小犯罪嫌疑人的范围,因此,在绑架、敲诈勒索、诈骗等案件中有较高运用价值。     

认识非语音信息在司法话者识别中的应用

通过介绍两起利用非语音信息最终辅助确认了说话人的司法话者识别检验案件,发现在说话人识别中,当待检语音无法满足语图比对条件时,充分利用非语音信息所揭示出的个体特性将有助于解决话者识别问题。得出了当待检语音条件不充分时,依靠非语音信息来辅助进行话者识别的方法。     

我国智能语音技术分析与专利池构建

作为战略性和前瞻性的重要新兴产业,智能语音技术领域一直是国内外学术界和产业界的研究焦点。通过采用专利信息分析的方法,研究我国智能语音技术发展现状,在此基础分析组建我国智能语音专利池的重要性,最后给出构建我国智能语音专利池的设想,为相关企业和政府部门推动我国智能语音专利池的发展提供相关参考。     

万维联合会提出下一代语音技术规范草案

【本刊讯】万维网联合会（World Wide Web Consortium）宣布下一代VoiceXML将包括说话者验证的技术规范。因特网标准制定团体万维网联合会称，它将提出VoiceXML3．0的技术规范草案，这项技术可以为用户在通过电话或者网络语音通讯进行商业谈判时提供话音识别校验服务。     

从专利视角看我国语音技术的发展

移动互联网和云计算的发展,语音技术得以发展和广泛应用。中国作为全球语音技术的主要市场,受到各大公司的关注。通过专利数据分析,发现我国是全球领军企业专利布局的重点地区,日本和美国企业布局了大量专利。国外领军企业在全球主要地区都布局了大量专利,而我国领军企业的专利布局主要集中在国内,全球竞争力较弱,如果产品出口可能面临较大的知识产权风险。     

辨证认识话者自动识别系统

为了警示近年来我国司法话者识别领域中出现的一些崇外、盲目追求快速与省事的苗头,结合话者自动识别系统的研究、应用状况,从语音的共性与个性、话者识别结果的相对性与绝对性出发,通过分析比对话者自动识别与语音识别所用的特征参数及实现过程,辨证分析了制约话者自动识别系统准确率的根本原因。指出了话者自动识别系统尚无法达到人们对其的期望,以及适合于司法诉讼领域的话者自动识别系统的发展方向。     

基于深度卷积神经网络的语音降噪研究

目的为了提高实际工作中获取到的音频资料中语音的质量,降低噪声对语音质量及可懂度的影响,提出了一种基于深度卷积神经网络的语音降噪模型。方法该模型通过卷积、加偏置、批量归一化、Relu激活的多层循环结构,能够有效地对低信噪比条件下语音中的洗衣机噪声、鼓掌噪声、汽车内部噪声等多种常见的环境噪声进行降噪处理。结果最终含噪语音经过模型处理后的MOS评分达到3.91分,其中最高分4.05分,最低分3.81分。结论该模型能够切实提高含噪语音的质量及可懂度,对于实际的公安工作、智慧警务建设、语音分析、语音文本识别等具有重要的意义和价值。     

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。     

Stress and Deception in Speech: Evaluating Layered Voice Analysis*

Abstract: This study was designed to evaluate commonly used voice stress analyzers—in this case the layered voice analysis (LVA) system. The research protocol involved the use of a speech database containing materials recorded while highly controlled deception and stress levels were systematically varied. Subjects were 24 each males/females (age range 18–63 years) drawn from a diverse population. All held strong views about some issue; they were required to make intense contradictory statements while believing that they would be heard/seen by peers. The LVA system was then evaluated by means of a double blind study using two types of examiners: a pair of scientists trained and certified by the manufacturer in the proper use of the system and two highly experienced LVA instructors provided by this same firm. The results showed that the “true positive” (or hit) rates for all examiners averaged near chance (42–56%) for all conditions, types of materials (e.g., stress vs. unstressed, truth vs. deception), and examiners (scientists vs. manufacturers). Most importantly, the false positive rate was very high, ranging from 40% to 65%. Sensitivity statistics confirmed that the LVA system operated at about chance levels in the detection of truth, deception, and the presence of high and low vocal stress states.     

INTERNET INTERMEDIARIES’ LIABILITY FOR ONLINE ILLEGAL HATE SPEECH

Considering the prevalence of online hate speech and its harm and risks to the targeted people, democratic discourse and public security, it is necessary to combat online hate speech. For this purpose, internet intermediaries play a crucial role as new governors of online speech. However, there is no universal definition of hate speech. Rules concerning this vary in different countries depending on their social, ethical, legal and religious backgrounds. The answer to the question of who can be liable for online hate speech also varies in different countries depending on the social, cultural, history, legal and political backgrounds. The First Amendment, cyberliberalism and the priority of promoting the emerging internet industry lead to the U.S. model, which offers intermediaries wide exemptions from liability for third-party illegal content. Conversely, the Chinese model of cyberpaternalism prefers to control online content on ideological, political and national security grounds through indirect methods, whereas the European Union (EU) and most European countries, including Germany, choose the middle ground to achieve balance between restricting online illegal hate speech and the freedom of speech as well as internet innovation. It is worth noting that there is a heated discussion on whether intermediary liability exemptions are still suitable for the world today, and there is a tendency in the EU to expand intermediary liability by imposing obligation on online platforms to tackle illegal hate speech. However, these reforms are again criticized as they could lead to erosion of the EU legal framework as well as privatization of law enforcement through algorithmic tools. Those critical issues relate to the central questions of whether intermediaries should be liable for user-generated illegal hate speech at all and, if so, how should they fulfill these liabilities? Based on the analysis of the different basic standpoints of cyberliberalists and cyberpaternalists on the internet regulation as well as the arguments of proponents and opponents of the intermediary liability exemptions, especially the debates over factual impracticality and legal restraints, impact on internet innovation and the chilling effect on freedom of speech in the case that intermediaries bear liabilities for illegal third-party content, the paper argues that the arguments for intermediary liability exemptions are not any more tenable or plausible in the web 3.0 era. The outdated intermediary immunity doctrine needs to be reformed and amended. Furthermore, intermediaries are becoming the new governors of online speech and platforms now have the power to curtail online hate speech. Thus, the attention should turn to the appropriate design of legal responsibilities of intermediaries. The possible suggestions could be the following three points: Imposing liability on intermediaries for illegal hate speech requires national law and international human rights norms as the outer boundary; openness, transparency and accountability as internal constraints; balance of multi-interests and involvement of multi-stakeholders in internet governance regime.     

基本权利的规范领域和保护程度对我国宪法第35条和第41条的规范比较

基本权利的规范领域和保护程度之间存在反比关系：规范领域愈宽，保护程度愈低；规范领域愈窄，保护程度愈高。我国宪法第35条规定的言论自由，其规范领域宽于宪法第41条规定的监督权，因此宪法对监督权的保护程度高于对言论自由的保护。基本权利对公权力裁量余地的限制，随着所涉及基本权利的不同而有所差异：公权力对言论自由的限制，需要提出充分的理由；对受保护程度更高的监督权的限制，需要提出更强有力的理由。宪法对监督权的高程度保护，体现了制宪者对民主监督的期盼和对民主建设的信心。     

不正当竞争规制与商业言论自由

正当竞争边界的模糊性与商业言论边界的不确定性,决定了不正当竞争规制与商业言论自由之间存在模糊难决的空间。不正当竞争边界的模糊性易导致不正当竞争规制过宽,仅依据不正当竞争法处理有关商业言论行为可能会导致基本权利价值受到损害。商业言论边界的不确定性使得欧美至今未能对商业言论进行准确的界定,也未形成统一的商业言论保护的原则和标准,其仅受到有限保护。不正当竞争规制的宽泛性与商业言论自由的有限性会不可避免地导致二者发生冲突。对此,欧美所进行的立法及实践表明,商业言论自由是有限度的,当商业言论涉及不正当竞争规制时,只有商业言论事关重大社会公共利益时才可能受到宪法保护。其立法和实践显示出法院根据不正当竞争法和宪法进行双重审查的特点,而依据宪法的基本权利价值进行考量是平衡二者冲突的关键之所在。这些立法和实践为我国商业言论保护提供了可资借鉴的经验。     

基于语言学音系例字的口音自动识别探究

目的以方言语音学为视角,通过计算机分析和选择模型训练数据,探究提高口音自动识别准确率及优化模型训练数据的方法。方法采用音系分析、语音信号处理、数学模型实验和统计的方法,对包含约81400段电子语音的37个方言点(每个方言点约2200段),逐一进行音系提炼、挑选音系例字、电子语音预处理和提取梅尔倒谱系数(MFCC),构建高斯混合模型(GMM)进行口音识别分析。结果从方言语音中提取的音系例字作为训练集(约260字)的识别模型可以较好地完成口音识别任务,对比任选300个例字作为训练集的识别模型,无论是识别准确度还是待测语音数量的要求都有显著优势。结论基于语言学音系例字的口音自动识别方法,已经完成37个方言点高斯混合模型的建立,可以用于口音识别中辅助辨别分析。     

从自由到平等:美国言论自由的现代转型

自1960年代开始,美国言论自由开启了从经典时期向现代的转型。在色情作品、仇恨言论和竞选经费三个领域,言论自由分别与性别平等、种族平等和财富平等正面相遇。通过把"平等"价值引入言论自由这一转型,使色情作品、仇恨言论和竞选经费从单纯的自由问题变为平等与自由间的平衡;同时,为了促进平等,它还强调法律和政策应告别形式中立,必须向弱势群体有所倾斜。这一转型相当于一场言论自由的"新政",终结了言论自由的洛克纳时代,重塑了言论自由的范式和议程,并对当代言论自由的发展产生持续和深远的影响。     

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.