Semi-Supervised Source Localization on Multiple-Manifolds with Distributed Microphones

TL;DR

This paper presents a semi-supervised Bayesian approach using Gaussian processes for source localization with distributed microphones, effectively combining labeled and unlabeled data without calibration in noisy, reverberant environments.

Contribution

It introduces a novel Gaussian process-based framework that models microphone relationships and unifies multi-microphone data for source localization without requiring calibration.

Findings

Effective in noisy and reverberant environments

Works with limited labeled data and abundant unlabeled data

Demonstrates accurate 2-D localization on real and simulated data

Abstract

The problem of source localization with ad hoc microphone networks in noisy and reverberant enclosures, given a training set of prerecorded measurements, is addressed in this paper. The training set is assumed to consist of a limited number of labelled measurements, attached with corresponding positions, and a larger amount of unlabelled measurements from unknown locations. However, microphone calibration is not required. We use a Bayesian inference approach for estimating a function that maps measurement-based feature vectors to the corresponding positions. The central issue is how to combine the information provided by the different microphones in a unified statistical framework. To address this challenge, we model this function using a Gaussian process with a covariance function that encapsulates both the connections between pairs of microphones and the relations among the samples in the training set. The parameters of the process are estimated by optimizing a maximum likelihood (ML) criterion. In addition, a recursive adaptation mechanism is derived where the new streaming measurements are used to update the model. Performance is demonstrated for 2-D localization of both simulated data and real-life recordings in a variety of reverberation and noise levels.