An Efficient Neural Network for Modeling Human Auditory Neurograms for Speech

TL;DR

This paper introduces a compact neural network that efficiently models human auditory neurograms, closely approximating classical models while enabling faster computation for neuroscience and audio processing.

Contribution

A novel deterministic convolutional encoder that replicates the Bruce et al. neurogram with reduced computational complexity and high fidelity.

Findings

Achieves close correspondence to classical neurogram models

Significantly reduces computational load

Enables real-time auditory neurogram simulation

Abstract

Classical auditory-periphery models, exemplified by Bruce et al., 2018, provide high-fidelity simulations but are stochastic and computationally demanding, limiting large-scale experimentation and low-latency use. Prior neural encoders approximate aspects of the periphery; however, few are explicitly trained to reproduce the deterministic, rate-domain neurogram , hindering like-for-like evaluation. We present a compact convolutional encoder that approximates the Bruce mean-rate pathway and maps audio to a multi-frequency neurogram. We deliberately omit stochastic spiking effects and focus on a deterministic mapping (identical outputs for identical inputs). Using a computationally efficient design, the encoder achieves close correspondence to the reference while significantly reducing computation, enabling efficient modeling and front-end processing for auditory neuroscience and audio signal processing applications.