Neuro-MSBG: An End-to-End Neural Model for Hearing Loss Simulation

TL;DR

Neuro-MSBG is a lightweight, end-to-end neural model that efficiently simulates hearing loss, maintaining speech intelligibility and quality while significantly reducing computation time for real-time applications.

Contribution

The paper introduces Neuro-MSBG, a novel neural model with personalized audiogram encoding that achieves fast, accurate hearing loss simulation suitable for real-time use.

Findings

Supports parallel inference for real-time simulation

Maintains high speech intelligibility and quality (SRCC of 0.9247 for STOI, 0.8671 for PESQ)

Reduces simulation runtime by 46 times

Abstract

Hearing loss simulation models are essential for hearing aid deployment. However, existing models have high computational complexity and latency, which limits real-time applications and lack direct integration with speech processing systems. To address these issues, we propose Neuro-MSBG, a lightweight end-to-end model with a personalized audiogram encoder for effective time-frequency modeling. Experiments show that Neuro-MSBG supports parallel inference and retains the intelligibility and perceptual quality of the original MSBG, with a Spearman's rank correlation coefficient (SRCC) of 0.9247 for Short-Time Objective Intelligibility (STOI) and 0.8671 for Perceptual Evaluation of Speech Quality (PESQ). Neuro-MSBG reduces simulation runtime by a factor of 46 (from 0.970 seconds to 0.021 seconds for a 1 second input), further demonstrating its efficiency and practicality.