Department of Communication Sciences and Disorders, University of Pittsburgh, Pittsburgh, PA 15213, United States of America.
J Neural Eng. 2019 Jul 23;16(5):056004. doi: 10.1088/1741-2552/ab1e01.
We investigate the biometric specificity of the frequency following response (FFR), an EEG marker of early auditory processing that reflects phase-locked activity from neural ensembles in the auditory cortex and subcortex (Chandrasekaran and Kraus 2010, Bidelman, 2015a, 2018, Coffey et al 2017b). Our objective is two-fold: demonstrate that the FFR contains information beyond stimulus properties and broad group-level markers, and to assess the practical viability of the FFR as a biometric across different sounds, auditory experiences, and recording days.
We trained the hidden Markov model (HMM) to decode listener identity from FFR spectro-temporal patterns across multiple frequency bands. Our dataset included FFRs from twenty native speakers of English or Mandarin Chinese (10 per group) listening to Mandarin Chinese tones across three EEG sessions separated by days. We decoded subject identity within the same auditory context (same tone and session) and across different stimuli and recording sessions.
The HMM decoded listeners for averaging sizes as small as one single FFR. However, model performance improved for larger averaging sizes (e.g. 25 FFRs), similarity in auditory context (same tone and day), and lack of familiarity with the sounds (i.e. native English relative to native Chinese listeners). Our results also revealed important biometric contributions from frequency bands in the cortical and subcortical EEG.
Our study provides the first deep and systematic biometric characterization of the FFR and provides the basis for biometric identification systems incorporating this neural signal.
我们研究了频率跟随反应（FFR）的生物识别特异性，FFR 是一种早期听觉处理的 EEG 标志物，反映了听觉皮层和皮层下神经群的锁相活动（Chandrasekaran 和 Kraus，2010 年；Bidelman，2015a，2018 年；Coffey 等人，2017b）。我们的目标有两个：一是证明 FFR 包含超出刺激特性和广泛的群体水平标记的信息，二是评估 FFR 在不同声音、听觉体验和记录日的生物识别中的实际可行性。
我们使用隐马尔可夫模型（HMM）来解码来自多个频带的 FFR 时频谱图案的听众身份。我们的数据集包括来自 20 位以英语或普通话为母语的人的 FFR，他们在三个 EEG 会话中分别聆听普通话声调，每个会话之间相隔一天。我们在相同的听觉环境（相同的音调和会话）和不同的刺激和记录会话中解码了听众的身份。
HMM 可以对小到单个 FFR 的平均大小进行听众解码。然而，对于较大的平均大小（例如 25 个 FFR）、听觉环境的相似性（相同的音调和天）以及对声音的不熟悉程度（即相对于母语为英语的听众，母语为汉语的听众），模型性能会提高。我们的结果还揭示了皮层和皮层下 EEG 频带对生物识别的重要贡献。
我们的研究首次对 FFR 进行了深入和系统的生物识别特征描述，并为包含这种神经信号的生物识别识别系统提供了基础。
