发表机构
Auditory Cognition and Computational Acoustics Lab; Shanghai Jiao Tong University; VUI Labs（听觉认知与计算声学实验室; 上海交通大学; VUI实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多通道语音增强受固定阵列配置限制问题，提出几何感知动态卷积框架，利用麦克风坐标转换固定阵列SE模型为阵列不变系统，经实验验证该框架能提升模型在不同阵列拓扑下的性能。
AI 中文摘要
多通道语音增强（SE）系统性能优于单通道方法，但受固定麦克风阵列配置限制，阻碍其在不同阵列几何形状设备上的实际部署。近期阵列无关SE方法虽解决了麦克风数量和排列问题，但未充分利用可用的显式阵列几何先验。本文提出几何感知动态卷积（Geo-DConv）框架，利用麦克风坐标将标准固定阵列SE模型转换为强大的阵列不变系统。在RealMAN多通道语音数据集上实验表明，该架构使两个常用固定阵列模型适应阵列不变设置，在不同阵列拓扑中性能持续提升。
英文摘要
Multi-channel speech enhancement (SE) systems exhibit superior performance over single-channel methods but are constrained to fixed microphone array configurations. This restricts their real-world deployment across devices with diverse array geometries. While recent array-agnostic SE methods address variable microphone numbers and permutations, they largely fail to exploit explicit array geometry priors when available, missing a crucial cue for optimal spatial filtering. A Geometry-Aware Dynamic Convolution (Geo-DConv) framework is proposed, which explicitly leverages microphone coordinates to transform standard fixed-array SE models into robust array-invariant systems. Experiments are conducted on the recent real-recorded RealMAN multi-channel speech dataset. Results demonstrate that the proposed architecture enables two widely used fixed-array models to adapt to array-invariant settings, with consistent performance improvements across diverse array topologies.
CommentsComments: 5 pages, 1 figure, 2 tables. Accepted at Interspeech 2026
