发布求助
文献互助 智能选刊 最新文献

2021 ISCA Symposium on Security and Privacy in Speech Communication最新文献

筛选
英文 中文
Open-Set Speaker Identification pipeline in live criminal investigations 现场刑事调查中的开式扬声器识别管道
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-5
Mael Fabien, P. Motlícek
{"title":"Open-Set Speaker Identification pipeline in live criminal investigations","authors":"Mael Fabien, P. Motlícek","doi":"10.21437/spsc.2021-5","DOIUrl":"https://doi.org/10.21437/spsc.2021-5","url":null,"abstract":"Speaker recognition has many applications in conversational data, including in forensic science where Law Enforcement Agencies (LEAs) aim to assess the identity of a speaker on a specific recorded telephone call. However, speaker identification (SID) systems require initial enrollment data, whereas LEAs might start a case with text or video evidence, and few to no enrollment data. In this paper, we introduce the ROXANNE simulated dataset, a multilingual corpus of acted telephone calls following a screenplay prepared by LEAs. We also present a process to build criminal networks from SID, by addressing practical constraints of these investigations. Our process reaches a speaker accuracy of 92.4% on the simulated data and a conversation accuracy of 84.9%. We finally offer some future directions for this work.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125503547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
ROXSD: a Simulated Dataset of Communication in Organized Crime ROXSD:有组织犯罪中通信的模拟数据集
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-7
Květoslav Malý, G. Backfried, F. Calderoni, J. Černocký, E. Dikici, Mael Fabien, Jan Hořínek, Joshua Hughes, Miro Janosik, Marek Kovác, P. Motlícek, Hoang H. Nguyen, Shantipriya Parida, Johan Rohdin, Miroslav Skácel, Sergej Zerr, D. Klakow, D. Zhu, Aravind Krishnan
{"title":"ROXSD: a Simulated Dataset of Communication in Organized Crime","authors":"Květoslav Malý, G. Backfried, F. Calderoni, J. Černocký, E. Dikici, Mael Fabien, Jan Hořínek, Joshua Hughes, Miro Janosik, Marek Kovác, P. Motlícek, Hoang H. Nguyen, Shantipriya Parida, Johan Rohdin, Miroslav Skácel, Sergej Zerr, D. Klakow, D. Zhu, Aravind Krishnan","doi":"10.21437/spsc.2021-7","DOIUrl":"https://doi.org/10.21437/spsc.2021-7","url":null,"abstract":"Criminal investigations contain sensitive and confidential material and are nonpublic by nature. Access to investigation data is very limited and restricted to only selected groups of individuals. Even for research purposes, data typically cannot be accessed freely. Within criminal investigations, data is still processed manually to a large extent. Solutions provided for automation of this processing — or even of individual processing steps — can be assumed to have a significant impact on the work of Law Enforcement Agencies (LEAs). Automation may effectively be key to handle large and complex amounts of data in an efficient manner under the typical operating conditions of LEAs. evaluation of novel tools and technologies for criminal investigations. ROXSD consists of a set of simulated intercepted telephone conversations in a variety of languages. The story follows a realistic setting and includes the conditions and constraints of a real investigation. The network topology corresponding to the conversations was created by partner LEAs to reflect various typical organized crime groups. Conversations have been transcribed carefully and annotated in the original language and in English. The dataset is expected to provide a sound basis for further research and is available to download for researchers under signed agreement.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127134575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
The Use of Audio Fingerprints for Authentication of Speakers on Speech Operated Interfaces 语音操作界面中音频指纹技术在说话人身份验证中的应用
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-2
Abraham Woubie, Tomas Bäckström, Pablo Pérez Zarazaga
{"title":"The Use of Audio Fingerprints for Authentication of Speakers on Speech Operated Interfaces","authors":"Abraham Woubie, Tomas Bäckström, Pablo Pérez Zarazaga","doi":"10.21437/spsc.2021-2","DOIUrl":"https://doi.org/10.21437/spsc.2021-2","url":null,"abstract":"In a multi-speaker and multi-device environment, we need acoustic fingerprint information for authentication between devices. Thus, in these kinds of environments, it is crucial to continuously check the authenticity of speakers and devices within a short duration since different speakers could join or leave the environment. In this work, we propose the provision of different levels of authentication to different speakers in a multi-speaker multi-device environment using acoustic audio fingerprint information. Firstly, the audio fingerprints are extracted continuously every few seconds. Then, the extracted fingerprints are passed to a speaker recognition module which checks if the fin-gerprint is enrolled for that particular environment or not. Finally, the proper level of authentication is provided for each speaker. Our experimental results on Voxceleb-1 dataset show that acoustic fingerprints can be successfully used for authentication purposes in a multi-speaker multi-device environment.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"128 26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121021939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Brave New World? Processing of personal data about employees under Art. 9 of GDPR in the context of human-robot interaction 美丽新世界?在人机交互的背景下，根据GDPR第9条处理员工个人数据
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-14
Ivo Emanuilov, K. Yordanova
{"title":"Brave New World? Processing of personal data about employees under Art. 9 of GDPR in the context of human-robot interaction","authors":"Ivo Emanuilov, K. Yordanova","doi":"10.21437/spsc.2021-14","DOIUrl":"https://doi.org/10.21437/spsc.2021-14","url":null,"abstract":"Ensuring safe and secure collaboration between robots and human workers is essential for the successful deployment of artificial intelligence on the factory shop floor. Any such interaction depends on actions such as perception, sensing and action on the part of the robot which are, essentially, enabled by the realtime processing of personal data concerning the factory workers. The majority of these data would easily fall into the special category of personal data under article 9 GDPR, e.g. as biometric data. This means that their processing would in principle be prohibited unless allowed by one of the explicit exceptions. In this paper, we analyse which of these grounds may be applicable, taking into account the specifics of these interactions on the shop floor, that is, in an employment context with high level of safety risks. We explore the problem focusing on selected scenarios which are inspired from real or planned deployments of human-robot collaborative manufacturing technologies in the industries of aerospace, maritime and automotive manufacturing.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125274446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Design Implications for Human-Machine Interactions from a Qualitative Pilot Study on Privacy 隐私权定性试点研究对人机交互设计的启示
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-16
Anna Leschanowsky, Birgit Brüggemeier, Nils Peters
{"title":"Design Implications for Human-Machine Interactions from a Qualitative Pilot Study on Privacy","authors":"Anna Leschanowsky, Birgit Brüggemeier, Nils Peters","doi":"10.21437/spsc.2021-16","DOIUrl":"https://doi.org/10.21437/spsc.2021-16","url":null,"abstract":"There are only few qualitative studies investigating privacy in Human-Machine Interaction (HMI). We conducted an exploratory qualitative study with the aim to better understand factors that influence privacy in HMI and how they relate to privacy in Human-to-Human Interaction (HHI). From there, we derived recommendations that can help designers to promote informed decision making and improve data sharing processes. We discuss the main distinguishing factors that were found carrying out semi-structured interviews. First, HMI contexts miss flexibility and proper protection strategies such that users can not easily protect themselves similar to what they are used to in HHI. Second, users were able to easily evaluate benefits of sharing data while risks remained elusive and difficult to assess. Further research is needed to understand the impact of this imbalance on users’ informed decision making.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128174855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Intuitive Privacy from Acoustic Reach: A Case for Networked Voice User-Interfaces 从声学到达的直观隐私:网络语音用户界面的一个案例
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-12
Tomas Bäckström, Sneha Das, Pablo Pérez Zarazaga, Johannes Fischer, R. Findling, S. Sigg, Le Ngu Nguyen
{"title":"Intuitive Privacy from Acoustic Reach: A Case for Networked Voice User-Interfaces","authors":"Tomas Bäckström, Sneha Das, Pablo Pérez Zarazaga, Johannes Fischer, R. Findling, S. Sigg, Le Ngu Nguyen","doi":"10.21437/spsc.2021-12","DOIUrl":"https://doi.org/10.21437/spsc.2021-12","url":null,"abstract":"The effect that advances in voice interface technologies have on privacy has not yet received the attention it deserves. Systems in which multiple devices collaborate to provide a unified user-interface amplify those worries about privacy. We discuss ethical implications of voice enabled devices on privacy in typical scenarios at home, office, in a car and in the public. From our findings, it follows that the reach of voice can be exploited as a feature to intuitively define the extent of privacy. In partic-ular, the acoustic reach of speech signals can serve as a feature for designing privacy-gentle voice user-interfaces which are intuitive to use. We argue that this approach poses reasonable technological requirements and establishes a natural experience of privacy which confirms intuitive perception.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132179841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Implications of the New Regulation Proposed by the European Commission on Automatic Content Moderation 欧盟委员会就自动内容审核提出的新规的影响
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-10
Vera Schmitt, Veronika Solopova, Vinicius Woloszyn, Jessica de Jesus de Pinho Pinhal
{"title":"Implications of the New Regulation Proposed by the European Commission on Automatic Content Moderation","authors":"Vera Schmitt, Veronika Solopova, Vinicius Woloszyn, Jessica de Jesus de Pinho Pinhal","doi":"10.21437/spsc.2021-10","DOIUrl":"https://doi.org/10.21437/spsc.2021-10","url":null,"abstract":"In April 2021 the European Commission (EC) proposed a new regulation to establish a regulatory structure for the risk assessment of Artificial Intelligence (AI) systems and applications. The intended goal of initiating a harmonised legal framework for the European Union (EU) poses new challenges in developing countermeasures for hate speech and fake news detection. This analysis investigates the implications of the proposed regulations on different automatic content moderation approaches such as flagging, blocking and filtering. The fuzzy nature of the risk categories causes major challenges for the risk categorisation task and leaves room for future improvements of the proposed regulations.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114189954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Federated Learning for Privacy Preserving On-Device Speaker Recognition 保护隐私的联邦学习设备上的说话人识别
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-11-10 DOI: 10.21437/spsc.2021-1
Abraham Woubie, Tom Bäckström
{"title":"Federated Learning for Privacy Preserving On-Device Speaker Recognition","authors":"Abraham Woubie, Tom Bäckström","doi":"10.21437/spsc.2021-1","DOIUrl":"https://doi.org/10.21437/spsc.2021-1","url":null,"abstract":"State-of-the-art speaker recognition systems are usually trained on a single computer using speech data collected from multiple users. However, these speech samples may contain private information which users are not willing to share. To overcome such potential breaches of privacy, we investigate the use of federated learning in speaker recognition. Distributed learning methods such as federated learning enable us to train a shared model without sharing the private data by training the models on edge devices where the data resides. In the proposed system, each edge device trains an individual model which is subse-quently sent to a secure aggregator. To provide contrasting data without the need for transmitting data, we use a generative adversarial network (GAN) to generate impostor data at the edge. Afterwards, the secure aggregator merges the individual models, builds a global model and transmits the global model to the edge devices through a main server. Experimental results on the Voxceleb-1 dataset show that the use of federated learning for speaker recognition system provides two advantages. Firstly, it retains privacy since the raw data does not leave the edge devices. Secondly, experimental results show that the aggregated model provides better average equal error rate than the individual models.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121826906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Revisiting Speech Content Privacy 重新审视言论内容隐私
2021 ISCA Symposium on Security and Privacy in Speech Communication Pub Date : 2021-10-13 DOI: 10.21437/spsc.2021-9
Jennifer Williams, J. Yamagishi, Paul-Gauthier Noé, C. V. Botinhão, J. Bonastre
{"title":"Revisiting Speech Content Privacy","authors":"Jennifer Williams, J. Yamagishi, Paul-Gauthier Noé, C. V. Botinhão, J. Bonastre","doi":"10.21437/spsc.2021-9","DOIUrl":"https://doi.org/10.21437/spsc.2021-9","url":null,"abstract":"In this paper, we discuss an important aspect of speech privacy: protecting spoken content. New capabilities from the field of machine learning provide a unique and timely opportunity to revisit speech content protection. There are many different applications of content privacy, even though this area has been under-explored in speech technology research. This paper presents several scenarios that indicate a need for speech content privacy even as the specific techniques to achieve content privacy may necessarily vary. Our discussion includes several different types of content privacy including recoverable and non-recoverable content. Finally, we introduce evaluation strategies as well as describe some of the difficulties that may be encountered.","PeriodicalId":185916,"journal":{"name":"2021 ISCA Symposium on Security and Privacy in Speech Communication","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121336178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信