Joint speaker localization and array calibration using expectation-maximization

Yuval Dorfan,Sharon Gannot,Ofer Schwartz

doi:10.1186/s13636-020-00177-1

Yuval Dorfan, Sharon Gannot + Show 1 more

Open Access

https://doi.org/10.1186/s13636-020-00177-1

Copy DOI

Abstract

Ad hoc acoustic networks comprising multiple nodes, each of which consists of several microphones, are addressed. From the ad hoc nature of the node constellation, microphone positions are unknown. Hence, typical tasks, such as localization, tracking, and beamforming, cannot be directly applied. To tackle this challenging joint multiple speaker localization and array calibration task, we propose a novel variant of the expectation-maximization (EM) algorithm. The coordinates of multiple arrays relative to an anchor array are blindly estimated using naturally uttered speech signals of multiple concurrent speakers. The speakers’ locations, relative to the anchor array, are also estimated. The inter-distances of the microphones in each array, as well their orientations, are assumed known, which is a reasonable assumption for many modern mobile devices (in outdoor and in a several indoor scenarios). The well-known initialization problem of the batch EM algorithm is circumvented by an incremental procedure, also derived here. The proposed algorithm is tested by an extensive simulation study.

Highlights

Localization and tracking using multiple arrays of sensors are often handled under the assumption that the locations of the microphone arrays are precisely known
We present a new way for self-initialization, which utilizes the collected data in an incremental fashion
We propose the following incremental procedure that was empirically shown to converge to the maximum likelihood estimation (MLE)

Summary

Introduction

Localization and tracking using multiple arrays of sensors are often handled under the assumption that the locations of the microphone arrays are precisely known. The recent deployment of ad hoc networks introduces a new challenge of estimating the array locations in parallel to routine tasks, such as speaker localization [1,2,3,4,5], noise or reverberation reduction [6,7,8], and speaker separation [9,10,11,12,13]. The solution is complex due to the amount of unknown parameters and the dependencies between them. Many scenarios do not even have a unique single solution, e.g., when the numbers of arrays or active sources are too small. The new algorithm combines two tasks: direct positioning determination (DPD) and calibration for ad hoc networks

Objectives

Methods

Results

Conclusion