Machine Learning Based Listener Classification and Authentication Using Frequency Following Responses to English Vowels for Biometric Applications

Auditory Evoked Potentials (AEPs) have recently gained attention as a biometric feature that may improve security and address reliability shortfalls of other commonly used biometric features. The objective of this paper is to investigate the accuracy with which subjects can be automatically identified or authenticated with machine learning (ML) techniques using a type of AEP known as the speech-evoked frequency following response (FFR). A thorough hyperparameter tuning is performed for the ML models, and more accurate discrimination between FFRs from different subjects is achieved compared to previous studies. The potential of using AEPs for listener authentication is also investigated.