当前位置: X-MOL 学术IEEE Trans. Dependable Secure Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
I sense you by Breath: Speaker Recognition via Breath Biometrics
IEEE Transactions on Dependable and Secure Computing ( IF 7.3 ) Pub Date : 2020-03-01 , DOI: 10.1109/tdsc.2017.2767587
Li Lu , Lingshuang Liu , Muhammad Jawad Hussain , Yongshuai Liu

Over last two decades, Speaker Recognition has primarily been focused on source, system, and prosodic features of the speech. The breath, however, has either been treated as a trivial part of the speech, or considered a noise entity. Our observation reveals that breath is a unique fingerprint of human respiratory system which offers overwhelming results for Speaker Recognition. Moreover, its passive nature, short-duration, fewer occurrences and simple processing results to a light-weight, text-independent and transparent system, which we articulate as BreathID. The breath features are extracted and classified by Mel Frequency Cepstral Coefficients, MFCC, based template matching technique. The verification is performed by a similarity based scheme, whose efficiency competes with classification algorithms. We process a data set collected from 50 users. Our system offers a 0.04 percent False Identification Rate, FIR, for Speaker Identification, and 0.12 percent False Acceptance Rate, FAR, and 0.15 percent False Rejection Rate, FRR, for Speaker Verification. We further evaluate our scheme under various practical modalities, like text in-dependence, replay scenario, users’ motion status (sitting and walking), recording equipment (03 smartphones and 02 microphones), recording period (08 months), and bilingual contents (English and Chinese). Though we use Matlab to formulate a fine-grained approach, we foresee breath biometric as a viable security measure for practical realizations.

中文翻译:

我通过呼吸感知你:通过呼吸生物识别技术识别说话者

在过去的二十年里,说话人识别主要关注语音的来源、系统和韵律特征。然而,呼吸要么被视为语音的一个微不足道的部分,要么被视为噪音实体。我们的观察表明,呼吸是人类呼吸系统的独特指纹,它为说话者识别提供了压倒性的结果。此外,它的被动性、持续时间短、出现次数少和处理简单,导致了一个轻量级、独立于文本和透明的系统,我们将其表述为 BreathID。呼吸特征通过基于梅尔频率倒谱系数(MFCC)的模板匹配技术进行提取和分类。验证由基于相似性的方案执行,其效率可与分类算法竞争。我们处理从 50 个用户收集的数据集。我们的系统提供 0.04% 的错误识别率 (FIR) 用于说话人识别,以及 0.12% 的错误接受率 (FAR) 和 0.15% 的错误拒绝率 (FRR),用于说话人验证。我们在各种实际模式下进一步评估我们的方案,如文本独立、重放场景、用户运动状态(坐和走)、录音设备(03 智能手机和 02 麦克风)、录音时间(08 个月)和双语内容(英文和中文)。尽管我们使用 Matlab 来制定细粒度的方法,但我们预见呼吸生物识别是一种可行的安全措施,可用于实际实现。15% 的错误拒绝率 (FRR),用于说话人验证。我们在各种实际模式下进一步评估我们的方案,如文本独立、重放场景、用户运动状态(坐和走)、录音设备(03 智能手机和 02 麦克风)、录音时间(08 个月)和双语内容(英文和中文)。尽管我们使用 Matlab 来制定细粒度的方法,但我们预见呼吸生物识别是一种可行的安全措施,可用于实际实现。15% 的错误拒绝率 (FRR),用于说话人验证。我们在各种实际模式下进一步评估我们的方案,如文本独立、重放场景、用户运动状态(坐和走)、录音设备(03 智能手机和 02 麦克风)、录音时间(08 个月)和双语内容(英文和中文)。尽管我们使用 Matlab 来制定细粒度的方法,但我们预见呼吸生物识别是一种可行的安全措施,可用于实际实现。
更新日期:2020-03-01
down
wechat
bug