Rethinking multi-spatial information for transferable adversarial attacks on speaker recognition systems

Adversarial attacks have been posing significant security concerns to intelligent systems,such as speaker recognition systems(SRSs).Most attacks assume the neural networks in the systems are known beforehand,while black-box attacks are proposed without such information to meet practical situations.Existing black-box attacks improve trans-ferability by integrating multiple models or training on multiple datasets,but these methods are costly.Motivated by the optimisation strategy with spatial information on the perturbed paths and samples,we propose a Dual Spatial Momentum Iterative Fast Gradient Sign Method(DS-MI-FGSM)to improve the transferability of black-box at-tacks against SRSs.Specifically,DS-MI-FGSM only needs a single data and one model as the input;by extending to the data and model neighbouring spaces,it generates adver-sarial examples against the integrating models.To reduce the risk of overfitting,DS-MI-FGSM also introduces gradient masking to improve transferability.The authors conduct extensive experiments regarding the speaker recognition task,and the results demonstrate the effectiveness of their method,which can achieve up to 92%attack success rate on the victim model in black-box scenarios with only one known model.

Chinese Native Speakers' Counterfactuals Revisited

This paper examines whether or not Chinese native speakers (CNSs) have difficulties in understanding English counterfactuals, whether CNSs have counterfactual reasoning problems in their own language, what the causes of these difficulties may be, and the problems in teaching English subjunctives. It also proposes on how to improve CNSs’ English counterfactual comprehension.

Language Teaching and Intercultural Communication:Teaching Korean Grammar to Non-native Speakers

Grounded upon the interactive relationship between intercultural communication(IC)and foreign language education and the recent gradual salience of communicative language teaching(CLT)in foreign language grammar learning sectors,the study reported in this paper deals with the issue of teaching Korean grammar to non-native speakers in terms of teaching Korean as a foreign language(TKFL).This paper attempts to examine and analyze several Korean language textbooks prepared for foreign learners of Korean,which is used overseas,especially in Hong Kong(HK).It is also attempted to evaluate the textbooks in terms of CLT and communicative competence.By doing so,we can further understand the methods of Korean grammar instruction provided to foreigners as a second language or a foreign language.

A Critique of Ali Shehadeh's Non-native Speakers'Production of Modified Comprehensible Output and Second Language Learning

This study examined the NNSs' ability of modifying their interlanguage utterances in modified comprehensible output to give response to other-initiation and self-initiation,which was studied in both NS-NNS and NNS-NNS interactions.It was the qualitative study by using two different tasks which were picture-dictation task and opinion-exchange task to collect the data.There were 32 participants whose age ranged of 22 to 37.The author proposed two hypotheses based on his expectation that NNS-NNS interactions would provide more opportunities for NNS participants to give comprehensible output for other-initiated clarification requests and self-initiated clarification attempts than NS-NNS interactions.The author was good at using numbers to illustrate and describe the data in his writing.

Analysis of Deaf Speakers’ Speech Signal for Understanding the Acoustic Characteristics by Territory Specific Utterances

An important concern with the deaf community is inability to hear partially or totally. This may affect the development of language during childhood, which limits their habitual existence. Consequently to facilitate such deaf speakers through certain assistive mechanism, an effort has been taken to understand the acoustic characteristics of deaf speakers by evaluating the territory specific utterances. Speech signals are acquired from 32 normal and 32 deaf speakers by uttering ten Indian native Tamil language words. The speech parameters like pitch, formants, signal-to-noise ratio, energy, intensity, jitter and shimmer are analyzed. From the results, it has been observed that the acoustic characteristics of deaf speakers differ significantly and their quantitative measure dominates the normal speakers for the words considered. The study also reveals that the informative part of speech in a normal and deaf speakers may be identified using the acoustic features. In addition, these attributes may be used for differential corrections of deaf speaker’s speech signal and facilitate listeners to understand the conveyed information.

著名的海德公园一角——Speakers’Corner

在英国伦敦的繁华市区,坐落着著名的海德公园。园内绿草如茵,鲜花缤纷;令人心驰神往的石雕掩映在花草树木丛中。空气清新,景色宜人,碧空如洗,白云悠闲,给人宽松敞亮之感。19世纪以来,在公园的东北角,形成了一块热闹的“自由论坛”——Speakers’Corner(演讲者之角)。每个星期天的下午,人们站在装肥皂用的木箱上发表演说。

The Intelligibility of Thai Speakers’ Pronunciation from Chinese Listeners’ Perspective

The intelligibility of Thai speakers’English pronunciation from Chinese listeners’perspectives have not been analyzed deeply in current researches.As is known to all,the interconnection between China and Thailand is greatly developed with the sup⁃port of‘One Belt and One Road initiative’.However,it is inevitable for non-native English speakers to encounter some pronuncia⁃tion problems,which would affect them to communicate with each other.As for Chinese English learners,Thai accent to some ex⁃tent would be a great challenge during the conversation with Thai speakers.In order to promote a better communication,it is neces⁃sary to analyze the origin of Thai speakers’English pronunciation problems.Therefore,this research based on the previous studies to categorize the common pronunciation problems among Thai speakers.However,there are numerous English learners in Thailand that have various language proficiency.In this respect,two Thai speakers with different IELTS scores have been selected for com⁃parison,and six postgraduate students in the Education University of Hong Kong are invited to serve as a listener.As a result,this research will base on the listeners’feedback to highlight some suggestions to enhance the intelligibility of Thai speakers’pronun⁃ciation.

Native/Non-native English Speakers’Attitudes:Addressing Learners’Goals and Needs Towards Pronunciation Issues

The study attempts to explore native and non-native English speakers’attitudes towards accents and pronunciation-related issues.The sample group surveyed is composed of non-native English speakers,specifically,Italian students studying at the University of Calabria(Italy)and native English speakers from Alberta University(Canada)and Florida Atlantic University(USA).An online link to a questionnaire was sent via email to all participants and was used as a research instrument to collect quantitative data.The research questions will investigate learners’attitudes in relation to the following aspects:accent and identity,beliefs about native/non-native accents,impact of pronunciation on communication,and learners’expectations towards pronunciation teaching.Firstly,mean scores in relation to the aforementioned aspects will be examined.Secondly,differences between native/non-native speakers’responses will be statistically analysed.Thirdly,non-native learners’responses will be correlated with their proficiency level in English to identify the extent to which language competence may affect learners’attitudes.The study aims to gain useful insights that may hopefully raise students and teachers’awareness of what models we expect learners to imitate and attain in the English language classroom,how appropriate and relevant these may be especially in the globalized English world where non-native speakers will increasingly use English in a diversity of forms to achieve their communicative goals.The preliminary results will be presented and pedagogical considerations suggested.

ELF Interactions Among Chinese, Greek, and Swiss Speakers of English

The paper concerns the issue of ELF （English as a lingua franca） in the European and Asian context. The authors start from a brief conceptual perspective to shed light on salient aspects related to ELF. Then, this paper discusses the study investigating the interactions among NNS （non-native speakers） of English in the naturalistic settings, namely in Zhangjiajie （China）, Masouri （Kalymnos/Greece）, and Unterwasser （Switzerland）. The main objective of the research based on the qualitative methodology was to analyze the ELF interactions from the linguistic point of view focusing on lexicogrammar and pragmatic features. The secondary objective was to establish whether the identified ELF features contributed to communication intelligibility. The obtained results indicated a few significant similarities with the Seidlhofer＇s list of the ELT characteristics. Furthermore, it was established in the study that the ELF features did not interfere with effective communication between interlocutors

An Efficient Text-Independent Speaker Identification Using Feature Fusion and Transformer Model

Automatic Speaker Identification(ASI)involves the process of distinguishing an audio stream associated with numerous speakers’utterances.Some common aspects,such as the framework difference,overlapping of different sound events,and the presence of various sound sources during recording,make the ASI task much more complicated and complex.This research proposes a deep learning model to improve the accuracy of the ASI system and reduce the model training time under limited computation resources.In this research,the performance of the transformer model is investigated.Seven audio features,chromagram,Mel-spectrogram,tonnetz,Mel-Frequency Cepstral Coefficients(MFCCs),delta MFCCs,delta-delta MFCCs and spectral contrast,are extracted from the ELSDSR,CSTRVCTK,and Ar-DAD,datasets.The evaluation of various experiments demonstrates that the best performance was achieved by the proposed transformer model using seven audio features on all datasets.For ELSDSR,CSTRVCTK,and Ar-DAD,the highest attained accuracies are 0.99,0.97,and 0.99,respectively.The experimental results reveal that the proposed technique can achieve the best performance for ASI problems.

Optical Ciphering Scheme for Cancellable Speaker Identification System

Most current security and authentication systems are based on personal biometrics.The security problem is a major issue in the field of biometric systems.This is due to the use in databases of the original biometrics.Then biometrics will forever be lost if these databases are attacked.Protecting privacy is the most important goal of cancelable biometrics.In order to protect privacy,therefore,cancelable biometrics should be non-invertible in such a way that no information can be inverted from the cancelable biometric templates stored in personal identification/verification databases.One methodology to achieve non-invertibility is the employment of non-invertible transforms.This work suggests an encryption process for cancellable speaker identification using a hybrid encryption system.This system includes the 3D Jigsaw transforms and Fractional Fourier Transform(FrFT).The proposed scheme is compared with the optical Double Random Phase Encoding(DRPE)encryption process.The evaluation of simulation results of cancellable biometrics shows that the algorithm proposed is secure,authoritative,and feasible.The encryption and cancelability effects are good and reveal good performance.Also,it introduces recommended security and robustness levels for its utilization for achieving efficient cancellable biometrics systems.

Voice Response Questionnaire System for Speaker Recognition Using Biometric Authentication Interface

The use of voice to perform biometric authentication is an importanttechnological development,because it is a non-invasive identification methodand does not require special hardware,so it is less likely to arouse user disgust.This study tries to apply the voice recognition technology to the speech-driveninteractive voice response questionnaire system aiming to upgrade the traditionalspeech system to an intelligent voice response questionnaire network so that thenew device may offer enterprises more precise data for customer relationshipmanagement(CRM).The intelligence-type voice response gadget is becominga new mobile channel at the current time,with functions of the questionnaireto be built in for the convenience of collecting information on local preferencesthat can be used for localized promotion and publicity.Authors of this study propose a framework using voice recognition and intelligent analysis models to identify target customers through voice messages gathered in the voice response questionnaire system;that is,transforming the traditional speech system to anintelligent voice complex.The speaker recognition system discussed hereemploys volume as the acoustic feature in endpoint detection as the computationload is usually low in this method.To correct two types of errors found in the endpoint detection practice because of ambient noise,this study suggests ways toimprove the situation.First,to reach high accuracy,this study follows a dynamictime warping(DTW)based method to gain speaker identification.Second,it isdevoted to avoiding any errors in endpoint detection by filtering noise from voicesignals before getting recognition and deleting any test utterances that might negatively affect the results of recognition.It is hoped that by so doing the recognitionrate is improved.According to the experimental results,the method proposed inthis research has a high recognition rate,whether it is on personal-level or industrial-level computers,and can reach the practical application standard.Therefore,the voice management system in this research can be regarded as Virtual customerservice staff to use.

NCTO Announces 6th Annual Meeting SPEAKERS

NCTO is delighted to announce the preliminary slate of speakers who will address NCTO Member Companies during the Annual Meeting in May 2009.

杨声器 Altec Lansing ACS500 Speakers:大声点!

如果你需要给你的高档多媒体PC配上一套具有丰富饱满声音的扬声器,那么Altec Lansing 399美元的ACS500Multimedia Speakers值得选用,这套扬声器提供了超重低音效果,并具有DolbyProLogic环绕立体声,只是需要占用一些桌面空间。 ACS500立式扬声器具有19英寸高,横截面积为5×7英寸。它们共享22.5W放大器和控制电路,以驱动各箱体内的四个扬声器。其中面朝前方的为一个3英寸中音扬声器和一个1英寸高频扬声器。

Efficiency in Teaching Speaker and Listener Repertoires:Comparing Three Instructional Sequences in Autistic Children

Previous studies have investigated the efficiency in teaching listener and speaker repertoires in children diagnosed with autism spectrum disorder(ASD).Some investigations focused on listener responding by function,feature,and class(LRFFC)and intraverbal by function,feature,and class(FFC).For some children,teaching intraverbal FFC was more efficient because it resulted in a better emergence effect of a related untaught repertoire(LRFFC).For other children,teaching LRFFC along with tacting pictures was more efficient,resulting in a better emergence effect of a related untaught repertoire(intraverbal FFC).In these cases,it is not clear whether the tact increased the efficiency of LRFFC training because a comparison with a condition in which tacts were not required was not conducted.This investigation consisted of a replication with two children diagnosed with ASD.Three instructional sequences were compared:teaching LRFFC-probing intraverbal;teaching LRFFC+tacts-probing intraverbal;teaching intraverbal-probing LRFFC.For a child,all sequences were equally efficient because all related untaught repertoires emerged without errors.However,the acquisition of intraverbals during training occurred with variability.In the case of the second child,the most efficient sequence consisted of teaching intraverbals,resulting in the emergence of LRFFC without errors.In both cases of teaching LRFFC,the emergence of related intraverbals was partial and acquisition of the trained repertoires occurred with variability.The case that did not demand tact responses was slightly more efficient.Data were discussed in the sense that the best instructional sequence may vary from learner to learner.

面向域外说话人适应场景的多层级解耦个性化语音合成

个性化语音合成任务旨在合成特定说话人音色的语音。传统方法在合成域外说话人语音时,与真实语音存在明显音色差异,解耦说话人特征仍较为困难。本文提出面向训练时未出现的域外说话人适应场景下的多层级解耦个性化语音合成方法,通过不同粒度特征融合,有效提升零资源条件下域外说话人语音合成性能。本文方法采用快速傅里叶卷积提取说话人全局特征,以提高模型对域外说话人的泛化能力,实现句子粒度的说话人解耦;借助语音识别模型解耦音素粒度说话人特征,并通过注意力机制捕捉音素级音色特征,实现音素粒度的说话人解耦。实验结果表明:在公开数据集AISHELL3上,本文方法对域外说话人在客观评价指标说话人特征向量余弦相似度上达到0.697,相比基线模型提高6.25%,有效提升对域外说话人音色特征建模能力。

多说话人分离与目标说话人提取的研究现状与展望

语音分离作为语音信号处理领域的前沿技术,具有重要的研究价值和广阔的应用前景。通常,麦克风拾取的信号包含有多个说话人的语音、噪声和混响。为了提升用户的听觉体验以及后端设备的处理性能,需要对混合信号进行语音分离。语音分离起源于著名的鸡尾酒会问题,旨在从混合信号中分离出说话人的语音信号。近年来,研究人员提出了大量的语音分离方法,显著提升了分离性能。本文对这些语音分离方法进行了系统的归纳和总结。首先,根据目标说话人的辅助信息利用与否,将语音分离方法分为两大类,即多说话人分离与目标说话人提取;其次,从传统到基于深度学习的角度,分别对多说话人分离和目标说话人提取两类方法进行详细介绍;最后,讨论了当前语音分离领域面临的一些挑战,并对未来的研究方向进行展望。

融合信息扰动与特征解耦的单样本语音转换

单样本语音转换的特性是利用单条目标说话人的语音样本即可实现身份的转换,但由于声学特征呈现复杂的相互作用和动态变化,现有方法难以充分将单样本语音中的说话人音色与其他声学特征解耦,导致转换音频在听觉上仍与源说话人的音色特征相似,存在说话人音色泄露情况。为此提出一种融合信息扰动与特征解耦的单样本语音转换模型,即IPFD-VC模型。首先,引入信息扰动模块对语音信号进行三次扰动操作,去除输入内容和韵律编码器中的冗余信息;其次,将处理后的语音信号送入各编码器,并结合最小化互信息策略进一步解耦声学特征,降低不同特征与说话人音色特征的相关性;最后通过解码器及声码器输出转换音频。实验结果表明:IPFD-VC模型转换音频的语音自然度和说话人相似度分别达到3.72和3.68,与目前先进的UUVC模型相比,梅尔倒谱失真降低0.26 dB。该模型能够有效对声学特征进行解耦,捕获目标说话人音色特征,同时保持源语言内容和韵律变化,降低说话人音色泄露风险。

说话人音频攻击与对抗技术研究综述

文中概括了说话人音频攻击与对抗技术的最新进展。由于说话人音频攻击已经成为语音应用安全的严重威胁,以WaveNet、Transformer和GAN三种模型在音频攻击技术中的应用作为节点,分别介绍以其为基础的音频攻击技术。音频对抗技术则以涵盖的攻击技术分为3类,分别是基础音频攻击、重放攻击和深度伪造攻击。系统地阐述了音频攻击与对抗技术的最新研究成果,并分析比较了各算法在不同条件下的优劣,同时还介绍了音频技术常用的数据集。最后结合该领域目前的研究现状,提出了说话人音频攻防对抗技术研究中亟待关注与研究的问题。

语篇主观性表征研究

基于语言主观性理论,本研究重点考察语篇的主观性表征。研究发现,语篇主观性表征有词汇、句法和语用等方面,它们共同承载着说写者的情感、态度、认识等主观自我成分。本研究与语言主观性现象的微观研究互补,为语篇层面语言主观性现象的整体研究提供研究思路,有利于深入挖掘说写者隐藏在语篇中的主观自我表征方式。