We propose auditory tagging, a novel method to enhance decoding performance in auditory brain-computer interface (BCI) paradigms. Drawing inspiration from steady-state visually evoked potentials (SSVEPs), auditory taggers involve embedding a steady frequency onto an auditory stimulus with the goal of eliciting a detectable neuronal response. In this work, we introduce three such approaches and evaluate them on the auditory intention decoding (AID) paradigm. In AID, subjects are primed with a question and potential target and non-target answer options are provided for this question. The BCI then decodes whether a given sample is a target or non-target. Despite the conceptual promise of the auditory taggers, experiment results did not reveal statistically significant improvements in decoding accuracy using the proposed tagging approaches. We discuss potential explanations for this observation and highlight possible avenues of improvement for future research.

Top

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Top