CNN-Based Modeling Reveals Temporal Brain Dynamics of Auditory Intensity Processing
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 34, 3190-3198
Abstract
Understanding how the human brain encodes auditory intensity remains a fundamental challenge, particularly at the level of single-trial hemodynamic responses. Traditional fNIRS analysis methods rely on fixed hemodynamic response models that collapse all trials into a single amplitude estimate, potentially overlooking rich temporal information. In this study, we introduce a Siamese convolutional neural network designed to decode intensity levels directly from full HbO trial waveforms, enabling a dynamic, waveform-level characterization of cortical responses. fNIRS data were collected from eighteen normal-hearing adults across two stimulus cohorts with three or four intensity levels plus a silence baseline. All analyses were performed using leave-one-subject-out validation to ensure cross-participant generalizability. Across participants, the network accurately discriminated intensity-level pairs (> 85% accuracy) and reconstructed full intensity rankings with robust performance in both cohorts. Training augmentation using cross-subject trial pairs further improved discrimination, revealing that intensity-related hemodynamic patterns are remarkably consistent across individuals with normal hearing. In contrast, disrupting temporal structure-either by randomizing trial order or by artificially jittering the alignment between stimulus onset and the extracted hemodynamic response resulted in substantial reductions in decoding accuracy, highlighting the critical role of time-locked waveform features in cortical intensity encoding. Together, these findings provide neural evidence that intensity perception is supported by highly consistent and temporally structured cortical responses in normal-hearing listeners. The results also demonstrate the value of dynamic, waveform-based deep learning approaches for fNIRS analysis and suggest a path toward more sensitive and physiologically grounded models of auditory processing.Keywords
Funding Information
- Contributing to Australian Scholarship and Science (CASS) Medicine and Science Grant
- Garnett Passe and Rodney Williams Memorial Foundation
- National Health and Medical Research Council
- Garnett Passe and Rodney Williams Memorial Foundation Mid-Career Fellowship
This publication has 34 references indexed in Scilit:
- Real time detection of cognitive load using fNIRS: A deep learning approachBiomedical Signal Processing and Control, 2022
- Investigation of deep convolutional neural network for classification of motor imagery fNIRS signals for BCI applicationsBiomedical Signal Processing and Control, 2020
- Siamese Neural Networks: An Overview2020
- Cortical correlates of speech intelligibility measured using functional near-infrared spectroscopy (fNIRS)Hearing Research, 2018
- Auditory cortex activation to natural speech and simulated cochlear implant speech measured with functional near-infrared spectroscopyHearing Research, 2014
- Frontal theta activity reflects distinct aspects of mental fatigueBiological Psychology, 2014
- Human auditory neuroimaging of intensity and loudnessHearing Research, 2014
- Auditory cortex activation is modulated by emotion: A functional near-infrared spectroscopy (fNIRS) studyNeuroImage, 2011
- Statistical parametric maps in functional imaging: A general linear approachHuman Brain Mapping, 1994
- Loudness, Its Definition, Measurement and Calculation*Bell System Technical Journal, 1933