One-Shot Distributed Node-Specific Signal Estimation with Non-Overlapping Latent Subspaces in Acoustic Sensor Networks

TL;DR

The paper introduces iDANSE, a one-shot, iterationless distributed algorithm for node-specific signal estimation in acoustic sensor networks, achieving centralized performance with minimal communication.

Contribution

It presents iDANSE, a novel one-shot algorithm that enables real-time, distributed, node-specific signal estimation with reduced communication in acoustic sensor networks.

Findings

iDANSE matches centralized algorithm performance in a single cycle

Devices exchange fewer signals than the number of sources

Validated through numerical simulations including speech enhancement

Abstract

A one-shot algorithm called iterationless DANSE (iDANSE) is introduced to perform distributed adaptive node-specific signal estimation (DANSE) in a fully connected wireless acoustic sensor network (WASN) deployed in an environment with non-overlapping latent signal subspaces. The iDANSE algorithm matches the performance of a centralized algorithm in a single processing cycle while devices exchange fused versions of their multichannel local microphone signals. Key advantages of iDANSE over currently available solutions are its iterationless nature, which favors deployment in real-time applications, and the fact that devices can exchange fewer fused signals than the number of latent sources in the environment. The proposed method is validated in numerical simulations including a speech enhancement scenario.