LiveProbe: Exploring Continuous Voice Liveness Detection via Phonemic Energy Response Patterns
LiveProbe: Exploring Continuous Voice Liveness Detection via Phonemic Energy Response Patterns
复制标题
LiveProbe：通过音素能量响应模式探索连续语音活跃度检测
DOI：
10.1109/jiot.2022.3228819
复制
发表时间：
2023-04
影响因子：
10.6
通讯作者：
John C. S. Lui
中科院分区：
文献类型：
--
作者：
Hangcheng Cao;Hongbo Jiang;Daibo Liu;Ruize Wang;Geyong Min;Jiangchuan Liu;Schahram Dustdar;John C. S. Lui
语音助手支持非接触式智能设备控制，因此可以作为人机交互的圣杯。然而，最近的研究表明，对手可以通过恶意的语音命令来操纵设备。这种安全风险是由于服务激活后只执行一次性的活性检测，缺乏安全保护模块造成的。因此，识别说话者类型（即，人类发音器或扬声器）在整个交互会话期间保护语音驱动的服务中是关键的。在本文中，我们提出了一个连续的语音活性检测方法LiveProbe，利用独特的能量响应模式在不同的语音生成机制引起的频带。LiveProbe背后的合理性体现在两个方面：人类发音器通过发音器官的精细协调运动重塑初始声音，发音器官充当带通滤波器，产生独特的能量响应;然而，扬声器的内部模块位置固定，无法再现这种响应特性。为此，我们首先研究导致频谱差异的两种扬声器背后的语音生成机制。然后，我们精心构建信号处理和深度学习模块来提取活性特征。特别是，我们的方法不会干扰正常的语音交互，也不需要携带定制的传感器。实验结果表明，该算法对潜在攻击的有效性为0.51%。
Voice assistants support contactless smart device control and thus act as a holy grail of human-computer interaction. However, recent studies reveal that an adversary can manipulate devices by vicious voice commands. This security risk is caused by only executing one-time liveness detection and lacking safeguard modules after service activation. Therefore, identifying speaker type (i.e., human articulators or loudspeakers) is critical in protecting voice-driven services during an entire interaction session. In this paper, we propose a continuous voice liveness detection approach LiveProbe, leveraging unique energy response patterns in frequency bands induced by distinct voice generation mechanisms. The rationality behind LiveProbe is presented in two aspects: human articulator reshapes initial voices by exquisitely coordinated movements of vocal organs, which act as band-pass filters generating unique energy responses; nevertheless, the internal modules of loudspeakers are position-fixed and cannot reproduce this response characteristic. To that end, we first work on voice generation mechanisms behind two-type speakers that cause spectrum differences. Then we elaborately construct signal processing and deep-learning modules to extract liveness features. Especially, our approach doesn’t interfere with normal voice interaction and needn’t to carry customized sensors. The experiment presents its effectiveness against potential attacks with a false acceptance rate of 0.51%..
登录
查看更多内容
DOI：
10.1201/b10345-5
发表时间：
2010-11
期刊：
Encyclopedia of Autism Spectrum Disorders
影响因子：
--
作者：
Kim-Anh Lê Cao;Z. Welham
通讯作者：
Kim-Anh Lê Cao;Z. Welham
DOI：
10.1145/3290605.3300828
发表时间：
2019-05
期刊：
Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
影响因子：
--
作者：
Il-Youp Kwak;J. Huh;S. Han;Iljoo Kim;J. Yoon
通讯作者：
Il-Youp Kwak;J. Huh;S. Han;Iljoo Kim;J. Yoon
DOI：
10.1145/3372297.3417254
发表时间：
2020-09
期刊：
Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security
影响因子：
--
作者：
Shu Wang;Jiahao Cao;Xu He;Kun Sun;Qi Li
通讯作者：
Shu Wang;Jiahao Cao;Xu He;Kun Sun;Qi Li
DOI：
10.1109/tasl.2007.899278
发表时间：
2007-07
期刊：
IEEE Transactions on Audio, Speech, and Language Processing
影响因子：
--
作者：
J. Ming;Timothy J. Hazen;James R. Glass;D. Reynolds
通讯作者：
J. Ming;Timothy J. Hazen;James R. Glass;D. Reynolds
DOI：
10.1007/978-3-319-99795-7_11
发表时间：
2018
期刊：
--
影响因子：
--
作者：
A. Berger
通讯作者：
A. Berger