A Joint Audio-Visual Approach to Audio Localization

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

227 Downloads (Pure)

Resumé

Localization of audio sources is an important research problem, e.g.,
to facilitate noise reduction. In the recent years, the problem has
been tackled using distributed microphone arrays (DMA). A common
approach is to apply direction-of-arrival (DOA) estimation on
each array (denoted as nodes), and then map the DOA estimates to
a location. In practice, however, the individual nodes contain few
microphones, limiting the DOA estimation accuracy and, thereby,
also the localization performance. We investigate a new approach,
where range estimates are also obtained and utilized from each node,
e.g., using time-of-flight cameras. Moreover, we propose an optimal
method for weighting such DOA and range information for audio
localization. Our experiments on both synthetic and real data show
that there is a clear, potential advantage of using the joint audiovisual
localization framework.
OriginalsprogEngelsk
TidsskriftI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
Sider (fra-til)454-458
Antal sider5
ISSN1520-6149
DOI
StatusUdgivet - 2015
Begivenhed40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 - Brisbane, Australien
Varighed: 19 apr. 201524 apr. 2015
Konferencens nummer: 2015

Konference

Konference40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015
Nummer2015
LandAustralien
ByBrisbane
Periode19/04/201524/04/2015

Fingerprint

Direction of arrival
Microphones
Noise abatement
Cameras
Experiments

Emneord

  • Localization
  • DOA
  • range
  • optimal weighting
  • distributed microphone arrays
  • time-of-flight camera

Citer dette

@inproceedings{bcbfeeaa6ec74733af11ed9df8dc34ae,
title = "A Joint Audio-Visual Approach to Audio Localization",
abstract = "Localization of audio sources is an important research problem, e.g., to facilitate noise reduction. In the recent years, the problem has been tackled using distributed microphone arrays (DMA). A common approach is to apply direction-of-arrival (DOA) estimation on each array (denoted as nodes), and then map the DOA estimates to a location. In practice, however, the individual nodes contain few microphones, limiting the DOA estimation accuracy and, thereby, also the localization performance. We investigate a new approach, where range estimates are also obtained and utilized from each node, e.g., using time-of-flight cameras. Moreover, we propose an optimal method for weighting such DOA and range information for audio localization. Our experiments on both synthetic and real data show that there is a clear, potential advantage of using the joint audiovisual localization framework.",
keywords = "Localization, DOA, range, optimal weighting, distributed microphone arrays, time-of-flight camera, localization, range, DOA, optimal weighting, distributed microphone arrays, time-of-flight camera",
author = "Jensen, {Jesper Rindom} and Christensen, {Mads Gr{\ae}sb{\o}ll}",
year = "2015",
doi = "10.1109/ICASSP.2015.7178010",
language = "English",
pages = "454--458",
journal = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",
issn = "1520-6149",
publisher = "IEEE Signal Processing Society",

}

TY - GEN

T1 - A Joint Audio-Visual Approach to Audio Localization

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Græsbøll

PY - 2015

Y1 - 2015

N2 - Localization of audio sources is an important research problem, e.g., to facilitate noise reduction. In the recent years, the problem has been tackled using distributed microphone arrays (DMA). A common approach is to apply direction-of-arrival (DOA) estimation on each array (denoted as nodes), and then map the DOA estimates to a location. In practice, however, the individual nodes contain few microphones, limiting the DOA estimation accuracy and, thereby, also the localization performance. We investigate a new approach, where range estimates are also obtained and utilized from each node, e.g., using time-of-flight cameras. Moreover, we propose an optimal method for weighting such DOA and range information for audio localization. Our experiments on both synthetic and real data show that there is a clear, potential advantage of using the joint audiovisual localization framework.

AB - Localization of audio sources is an important research problem, e.g., to facilitate noise reduction. In the recent years, the problem has been tackled using distributed microphone arrays (DMA). A common approach is to apply direction-of-arrival (DOA) estimation on each array (denoted as nodes), and then map the DOA estimates to a location. In practice, however, the individual nodes contain few microphones, limiting the DOA estimation accuracy and, thereby, also the localization performance. We investigate a new approach, where range estimates are also obtained and utilized from each node, e.g., using time-of-flight cameras. Moreover, we propose an optimal method for weighting such DOA and range information for audio localization. Our experiments on both synthetic and real data show that there is a clear, potential advantage of using the joint audiovisual localization framework.

KW - Localization

KW - DOA

KW - range

KW - optimal weighting

KW - distributed microphone arrays

KW - time-of-flight camera

KW - localization

KW - range

KW - DOA

KW - optimal weighting

KW - distributed microphone arrays

KW - time-of-flight camera

U2 - 10.1109/ICASSP.2015.7178010

DO - 10.1109/ICASSP.2015.7178010

M3 - Conference article in Journal

SP - 454

EP - 458

JO - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

JF - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SN - 1520-6149

ER -