ABSE-NET：用于开放式助听器中主动双耳语音增强的轻量级神经模型
ABSE-NET: A Lightweight Neural Model for Active Binaural Speech Enhancement in Open-Fit Hearing Aids
浏览论文内容
中文总结 AI 辅助
本文针对开放式助听器的声泄漏问题，提出将ANC与BSE结合的轻量级ABSE-NET框架，级联BMVDR与带特征融合模块的LNN，无需入耳麦克风，性能优于现有最先进方法。
中文摘要 AI 辅助
开放式助听器因佩戴舒适度佳而受到越来越多关注，但该设计不可避免地导致声泄漏进入耳道，降低了现有双耳语音增强（BSE）的性能。为此，本文提出ABSE-NET，一种将主动噪声控制（ANC）与BSE相结合的主动BSE框架，用于联合增强目标语音并抑制声泄漏。ABSE-NET的流程级联了双耳最小方差无失真响应（BMVDR）与轻量级神经网络（LNN），前者实现粗BSE，后者同时消除声泄漏并补偿BMVDR引起的失真。LNN采用带特征融合模块的编解码器，该模块包含时频依赖学习和卷积注意力块。与传统通过自适应滤波实现的BSE+ANC方案不同，ABSE-NET在实际部署中不需要入耳麦克风。实验验证了其优于现有最先进方法的性能，代码仓库为此https URL。
英文摘要
Open-fit hearing aids have attracted growing attention due to their superior wearing comfort. However, the open-fit design inevitably causes acoustic leakage into the ear canal, degrading the performance of existing binaural speech enhancement (BSE). To this end, we propose ABSE-NET, an active BSE framework integrating active noise control (ANC) with BSE to jointly enhance target speech and suppress acoustic leakage. The ABSE-NET pipeline cascades a binaural MVDR (BMVDR) with a lightweight neural network (LNN). The former achieves a coarse BSE, whereas the latter simultaneously cancels acoustic leakage and compensates for BMVDR-induced distortion. The LNN uses an encoder-decoder with a feature fusion module, which includes frequency-time dependency learning and convolutional attention blocks. Unlike traditional BSE+ANC solutions via adaptive filtering, ABSE-NET needs no in-ear microphone in practical deployment. Experiments validate its superiority over state-of-the-art methods. Code repository: https://github.com/Bream101/ABSE-NET.
发表机构
- College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）
- College of Electronic and Information Engineering, Inner Mongolia University（内蒙古大学电子与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。
