The Catcher in the Field: A Fieldprint based Spoofing Detection for Text-Independent Speaker Verification
The Catcher in the Field: A Fieldprint based Spoofing Detection for Text-Independent Speaker Verification
复制标题
DOI：
10.1145/3319535.3354248
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Chen Yan;Yan Long;Xiaoyu Ji;Wenyuan Xu
中科院分区：
文献类型：
--
作者：
Chen Yan;Yan Long;Xiaoyu Ji;Wenyuan Xu
随着语音越来越多地用于敏感操作，验证语音输入的身份非常重要。传统的方法集中于通过语音的频谱特征来区分个体（例如，声纹），但不能科普欺骗攻击，从而恶意攻击者合成的声音几乎相同的声纹的受害者或简单地replaysit. This本文提出CaField，一个文本无关的说话人验证方法来检测基于语音欺骗攻击的目标，实现两个看似矛盾的要求：可用性和安全性。CaField的关键见解是利用嵌入声场中的声学生物特征来构建“fieldprint”，即，声音在空气中传播时产生的声能的物理场，类似于“声纹”。我们发现扬声器（人类或扬声器）之间的场印可能是不同的，因此我们可以检测到用于来自真实用户的欺骗攻击的扬声器。我们对20人和8个扬声器的数据集进行的评估表明，通过依靠两个板载麦克风在用户与智能手机交谈时对声场进行采样，CaField在多个会话和各种语音输入中实现了99.16%的检测准确率和0.85%的等误差率（EER）。CaField支持8~kHz的低音频采样率，并对各种因素（包括手机位移、用户姿势、录音环境等）具有鲁棒性。
Verifying the identity of voice inputs is important as voices are increasingly used for sensitive operations. Traditional methods focus on differentiating individuals via the spectrographic features of voices (e.g., voiceprint), yet cannot cope with spoofing attacks, whereby a malicious attacker synthesizes the voice with almost the same voiceprint of a victim or simply replays it. This paper proposes CaField, a text-independent speaker verification method to detect loudspeaker-based voice spoofing attacks with the goal of achieving two seemingly conflicting requirements: usability and security. The key insight of CaField is to construct "fieldprint'' with the acoustic biometrics embedded in sound fields, i.e., a physical field of acoustic energy created as the sound propagates over the air, as analogous to "voiceprint''. We find that fieldprints can be distinctive between speakers (either humans or loudspeakers), and thus we may detect the speakers being used for spoofing attacks from the authentic users. Our evaluation on a dataset of 20 people and 8 loudspeakers shows that by relying on two on-board microphones to sample sound fields while users talk to the smartphones, CaField achieves a detection accuracy of 99.16% and an equal error rate (EER) of 0.85% across multiple sessions and various voice inputs. CaField supports low audio sample rates at 8~kHz and is robust to various factors including phone displacement, user posture, recording environment, etc.