Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization

Andreas Brendel; Bracha Laufer-Goldshtein; Sharon Gannot; Ronen Talmon; Walter Kellermann

doi:10.1109/icassp.2019.8683640

Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization

Andreas Brendel, Bracha Laufer-Goldshtein, Sharon Gannot, Ronen Talmon, Walter Kellermann

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

This paper investigates localization of an arbitrary number of simultaneously active speakers in an acoustic enclosure. We propose an algorithm capable of estimating the number of speakers, using reliability information to obtain robust estimation results in adverse acoustic scenarios and estimating individual probability distributions describing the position of each speaker using convex geometry tools. To this end, we start from an established algorithm for localization of acoustic sources based on the EM algorithm. There, the estimation of the number of sources as well as the handling of reverberation has not been addressed sufficiently. We show improvement in the localization of a higher number of sources and in the robustness in adverse conditions including interference from competing speakers, reverberation and noise.

Original language	English
Title of host publication	2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7898-7902
Number of pages	5
ISBN (Electronic)	9781479981311
DOIs	https://doi.org/10.1109/icassp.2019.8683640
State	Published - May 2019
Event	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom Duration: 12 May 2019 → 17 May 2019

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2019-May
ISSN (Print)	1520-6149

Conference

Conference	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Country/Territory	United Kingdom
City	Brighton
Period	12/05/19 → 17/05/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Funding

This work was supported by DFG under contract no <Ke890/10-1> within the Research Unit FOR2457 ”Acoustic Sensor Networks”

Funders	Funder number
Deutsche Forschungsgemeinschaft	<Ke890/10-1

Keywords

Acoustic source localization
EM algorithm
diarization
number of speakers estimation

Access to Document

10.1109/icassp.2019.8683640

Cite this

Brendel, A., Laufer-Goldshtein, B., Gannot, S., Talmon, R., & Kellermann, W. (2019). Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 7898-7902). Article 8683640 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icassp.2019.8683640

Brendel, Andreas ; Laufer-Goldshtein, Bracha ; Gannot, Sharon et al. / Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 7898-7902 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{88190d8a9b334e26b640373713faefdc,

title = "Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization",

abstract = "This paper investigates localization of an arbitrary number of simultaneously active speakers in an acoustic enclosure. We propose an algorithm capable of estimating the number of speakers, using reliability information to obtain robust estimation results in adverse acoustic scenarios and estimating individual probability distributions describing the position of each speaker using convex geometry tools. To this end, we start from an established algorithm for localization of acoustic sources based on the EM algorithm. There, the estimation of the number of sources as well as the handling of reverberation has not been addressed sufficiently. We show improvement in the localization of a higher number of sources and in the robustness in adverse conditions including interference from competing speakers, reverberation and noise.",

keywords = "Acoustic source localization, EM algorithm, diarization, number of speakers estimation",

author = "Andreas Brendel and Bracha Laufer-Goldshtein and Sharon Gannot and Ronen Talmon and Walter Kellermann",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",

year = "2019",

month = may,

doi = "10.1109/icassp.2019.8683640",

language = "אנגלית",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7898--7902",

booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

address = "ארצות הברית",

}

Brendel, A, Laufer-Goldshtein, B, Gannot, S, Talmon, R & Kellermann, W 2019, Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683640, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 7898-7902, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12/05/19. https://doi.org/10.1109/icassp.2019.8683640

Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization. / Brendel, Andreas; Laufer-Goldshtein, Bracha; Gannot, Sharon et al.
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 7898-7902 8683640 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization

AU - Brendel, Andreas

AU - Laufer-Goldshtein, Bracha

AU - Gannot, Sharon

AU - Talmon, Ronen

AU - Kellermann, Walter

PY - 2019/5

Y1 - 2019/5

N2 - This paper investigates localization of an arbitrary number of simultaneously active speakers in an acoustic enclosure. We propose an algorithm capable of estimating the number of speakers, using reliability information to obtain robust estimation results in adverse acoustic scenarios and estimating individual probability distributions describing the position of each speaker using convex geometry tools. To this end, we start from an established algorithm for localization of acoustic sources based on the EM algorithm. There, the estimation of the number of sources as well as the handling of reverberation has not been addressed sufficiently. We show improvement in the localization of a higher number of sources and in the robustness in adverse conditions including interference from competing speakers, reverberation and noise.

AB - This paper investigates localization of an arbitrary number of simultaneously active speakers in an acoustic enclosure. We propose an algorithm capable of estimating the number of speakers, using reliability information to obtain robust estimation results in adverse acoustic scenarios and estimating individual probability distributions describing the position of each speaker using convex geometry tools. To this end, we start from an established algorithm for localization of acoustic sources based on the EM algorithm. There, the estimation of the number of sources as well as the handling of reverberation has not been addressed sufficiently. We show improvement in the localization of a higher number of sources and in the robustness in adverse conditions including interference from competing speakers, reverberation and noise.

KW - Acoustic source localization

KW - EM algorithm

KW - diarization

KW - number of speakers estimation

UR - http://www.scopus.com/inward/record.url?scp=85068962276&partnerID=8YFLogxK

U2 - 10.1109/icassp.2019.8683640

DO - 10.1109/icassp.2019.8683640

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85068962276

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 7898

EP - 7902

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019

Y2 - 12 May 2019 through 17 May 2019

ER -

Brendel A, Laufer-Goldshtein B, Gannot S, Talmon R, Kellermann W. Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 7898-7902. 8683640. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/icassp.2019.8683640

Localization of an Unknown Number of Speakers in Adverse Acoustic Conditions Using Reliability Information and Diarization

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this