A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound
Abstract
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 causal neural network trained to map binaural acoustic waveforms directly to high-sample-rate EEG. The model was trained on approximately 250 hours of EEG data from 92 subjects, with varied electrode montages and stimuli spanning tonebursts, speech, and music. 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. The model-predicted BIC metrics closely resembled the values reported in the literature. These findings demonstrate that a single audio-to-EEG model can capture auditory physiology across paradigms and timescales, supporting future in silico experimentation and hearing technology applications.
Related
- Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices
- Spatiotemporal transcriptomic dynamic across the auditory pathway from young to old age in 5xFAD Alzheimer disease mice
- Multiscale Network Disruption of Auditory-Language Circuits Underlying Auditory Hallucinations in Schizophrenia
- Front-end and Back-end Computational Modeling of 40-Hz Auditory Steady-State Response Abnormalities in Schizophrenia
- Auditory brainstem response amplitude predicts age-related forward masking temporal-processing deficits in normal-hearing listeners
BibTeX
@misc{stoll2026deep,
title = {{A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound}},
author = {Thomas J Stoll and Ross K Maddox},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20595},
eprint = {2609.20595},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20595},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound
AU - Thomas J Stoll
AU - Ross K Maddox
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.20595
UR - https://arxiv.org/abs/2609.20595
AB - 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 causal neural network trained to map binaural acoustic waveforms directly to high-sample-rate EEG. The model was trained on approximately 250 hours of EEG data from 92 subjects, with varied electrode montages and stimuli spanning tonebursts, speech, and music. 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. The model-predicted BIC metrics closely resembled the values reported in the literature. These findings demonstrate that a single audio-to-EEG model can capture auditory physiology across paradigms and timescales, supporting future in silico experimentation and hearing technology applications.
ER -