轻量神经模型实现高保真听力损失仿真，实时性提升46倍。
Neuro-MSBG: An End-to-End Neural Model for Hearing Loss Simulation
- 基于个性化听觉图编码的端到端模型，支持并行推理
- 保持原MSBG的语音可懂度与感知质量，相关系数达0.92（STOI）
- 1秒音频仿真时间从0.97秒降至0.021秒，适合嵌入式系统
听力损失仿真模型对助听器部署至关重要。然而现有模型计算复杂度高、延迟大，难以实现实时应用，且难以直接集成至语音处理系统。为此，我们提出Neuro-MSBG，一种轻量级端到端模型，采用个性化听觉图编码器实现高效的时频建模。实验表明，Neuro-MSBG支持并行推理，保留了原始MSBG的可懂度与感知质量，短时客观可懂度（STOI）的斯皮尔曼等级相关系数（SRCC）为0.9247，感知语音质量评估（PESQ）为0.8671。该模型将仿真耗时降低46倍（1秒输入从0.970秒降至0.021秒），显著提升效率与实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。