Geometrically Informed Graph Neural Networks for Distributed Speech Enhancement in Challenging Acoustic Environments
Shih‐Hau Fang, Po-Han Li, Hau-Hsiang Jung, Syu‐Siang Wang · IEEE Sensors Letters · 2025
Speech signals face challenges in the presence of ambient sounds, encompassing factors like reverberation and diffuse noise, leading to compromises in clarity and intelligibility. Taking inspiration from the effectiveness of human binaural hearing, researchers have delved into the exploration of distributed speech enhancement (DSE) processors on the distributed microphone system. Despite the achievements of previous approaches, challenges remain, especially in reducing noise from speech signals and improving model interpretability. This study introduces an innovative geometrically informed graph neural network (GIGNN) designed for DSE tasks. The distinct advantage of GIGNN lies in the capability of GNNs to visualize structured data, proving effective in capturing a wide array of spatiotemporal interactions. Additionally, we assess the effectiveness of geometrically informed spatial matrices within GNNs in our evaluation. Experimental validation in varying signal-to-noise ratios in real-life scenarios underscores the potential of GIGNN.