Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data

Zonglong Bai; Jinwei Sun; Jesper Rindom Jensen; Mads Græsbøll Christensen

doi:10.23919/EUSIPCO.2019.8903069

Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data

Zonglong Bai, Jinwei Sun, Jesper Rindom Jensen, Mads Græsbøll Christensen

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

2 Citationer (Scopus)

Abstract

In this paper, the problems of indoor sound source
localization using a wireless acoustic sensor network are addressed and a new sparse Bayesian learning based algorithm is
proposed. Using time delays for the direct paths from candidate source locations to microphone nodes, the proposed algorithm estimates the most likely source location. To reduce the amount of data that must be exchanged between microphone nodes, a Gaussian measurement matrix is multiplied on to each channel and the proposed method operates directly on the compressed data. This is achieved by exploiting sparsity in both the frequency and space domains. The performance is analysed in numerical simulations, where the performance as a function of the reverberation times in investigated, and the results show that the proposed algorithm is robust to reverberation.

Originalsprog	Engelsk
Titel	2019 27th European Signal Processing Conference (EUSIPCO)
Forlag	IEEE
Publikationsdato	2019
Artikelnummer	8903069
ISBN (Trykt)	978-90-827970-2-2 (USB)
ISBN (Elektronisk)	978-9-0827-9703-9
DOI	https://doi.org/10.23919/EUSIPCO.2019.8903069
Status	Udgivet - 2019
Begivenhed	27th European Signal Processing Conference, EUSIPCO 2019 - Coruña, Spanien Varighed: 2 sep. 2019 → 6 sep. 2019

Konference

Konference	27th European Signal Processing Conference, EUSIPCO 2019
Land/Område	Spanien
By	Coruña
Periode	02/09/2019 → 06/09/2019

Navn	Proceedings of the European Signal Processing Conference
ISSN	2076-1465

Emneord

sound source localization
sparse Bayesian learning
array signal processing
reverberation

Adgang til dokumentet

10.23919/EUSIPCO.2019.8903069

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Sound PrOcessing for Robots and Drones in the fourth industrial revolution
Jensen, J. R.
01/01/2018 → 31/12/2020
Projekter: Projekt › Forskning

Citationsformater

@inproceedings{fae0846926184f7b82e9a4dcdfc85eb0,

title = "Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data",

abstract = "In this paper, the problems of indoor sound source localization using a wireless acoustic sensor network are addressed and a new sparse Bayesian learning based algorithm is proposed. Using time delays for the direct paths from candidate source locations to microphone nodes, the proposed algorithm estimates the most likely source location. To reduce the amount of data that must be exchanged between microphone nodes, a Gaussian measurement matrix is multiplied on to each channel and the proposed method operates directly on the compressed data. This is achieved by exploiting sparsity in both the frequency and space domains. The performance is analysed in numerical simulations, where the performance as a function of the reverberation times in investigated, and the results show that the proposed algorithm is robust to reverberation.",

keywords = "sound source localization, sparse Bayesian learning, array signal processing, reverberation",

author = "Zonglong Bai and Jinwei Sun and Jensen, {Jesper Rindom} and Christensen, {Mads Gr{\ae}sb{\o}ll}",

year = "2019",

doi = "10.23919/EUSIPCO.2019.8903069",

language = "English",

isbn = "978-90-827970-2-2 (USB)",

series = "Proceedings of the European Signal Processing Conference",

publisher = "IEEE",

booktitle = "2019 27th European Signal Processing Conference (EUSIPCO)",

address = "United States",

note = "27th European Signal Processing Conference, EUSIPCO 2019 ; Conference date: 02-09-2019 Through 06-09-2019",

}

Bai, Z, Sun, J, Jensen, JR & Christensen, MG 2019, Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data. i 2019 27th European Signal Processing Conference (EUSIPCO)., 8903069, IEEE, Proceedings of the European Signal Processing Conference, 27th European Signal Processing Conference, EUSIPCO 2019, Coruña, Spanien, 02/09/2019. https://doi.org/10.23919/EUSIPCO.2019.8903069

Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data. / Bai, Zonglong; Sun, Jinwei; Jensen, Jesper Rindom et al.
2019 27th European Signal Processing Conference (EUSIPCO). IEEE, 2019. 8903069 (Proceedings of the European Signal Processing Conference).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data

AU - Bai, Zonglong

AU - Sun, Jinwei

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Græsbøll

PY - 2019

Y1 - 2019

N2 - In this paper, the problems of indoor sound source localization using a wireless acoustic sensor network are addressed and a new sparse Bayesian learning based algorithm is proposed. Using time delays for the direct paths from candidate source locations to microphone nodes, the proposed algorithm estimates the most likely source location. To reduce the amount of data that must be exchanged between microphone nodes, a Gaussian measurement matrix is multiplied on to each channel and the proposed method operates directly on the compressed data. This is achieved by exploiting sparsity in both the frequency and space domains. The performance is analysed in numerical simulations, where the performance as a function of the reverberation times in investigated, and the results show that the proposed algorithm is robust to reverberation.

AB - In this paper, the problems of indoor sound source localization using a wireless acoustic sensor network are addressed and a new sparse Bayesian learning based algorithm is proposed. Using time delays for the direct paths from candidate source locations to microphone nodes, the proposed algorithm estimates the most likely source location. To reduce the amount of data that must be exchanged between microphone nodes, a Gaussian measurement matrix is multiplied on to each channel and the proposed method operates directly on the compressed data. This is achieved by exploiting sparsity in both the frequency and space domains. The performance is analysed in numerical simulations, where the performance as a function of the reverberation times in investigated, and the results show that the proposed algorithm is robust to reverberation.

KW - sound source localization

KW - sparse Bayesian learning

KW - array signal processing

KW - reverberation

U2 - 10.23919/EUSIPCO.2019.8903069

DO - 10.23919/EUSIPCO.2019.8903069

M3 - Article in proceeding

SN - 978-90-827970-2-2 (USB)

T3 - Proceedings of the European Signal Processing Conference

BT - 2019 27th European Signal Processing Conference (EUSIPCO)

PB - IEEE

T2 - 27th European Signal Processing Conference, EUSIPCO 2019

Y2 - 2 September 2019 through 6 September 2019

ER -

Indoor Sound Source Localization based on Sparse Bayesian Learning and Compressed Data

Abstract

Konference

Emneord

Adgang til dokumentet

AUB Link

Fingeraftryk

Projekter

Sound PrOcessing for Robots and Drones in the fourth industrial revolution

Citationsformater