A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound

Computational models of auditory physiology commonly target specific responses or stages of the auditory pathway, limiting their ability to integrate findings across experimental paradigms and neural timescales. We present a foundation model of human auditory electrophysiology: a temporally causal neural network trained to map binaural acoustic waveforms directly to high-sample-rate EEG. The model was trained on approximately 250 hours from 92 subjects, with stimuli spanning tonebursts, speech, music, and varied electrode montages. Without evaluation-specific fine-tuning or subject calibration, we tested whether the model recovered effects of stimulus rate, frequency, and presentation method on auditory brainstem responses (ABRs); subcortical and cortical temporal response functions (TRFs) to continuous speech; and the click-evoked binaural interaction component (BIC). Predicted ABRs and TRFs reproduced established response morphology and stimulus-dependent effects, with model–grand-average correlations falling within the corresponding subject-level human distributions. Additionally, the model-predicted BIC closely resembled the values reported in the literature. These findings demonstrate that a single audio-to-EEG model trained across diverse subjects, stimuli, and recording configurations can capture auditory physiology across paradigms and timescales, supporting future \textit{in-silico} experimentation and hearing technology applications.