TY - JOUR
T1 - DA-MUSIC
T2 - Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm
AU - Merkofer, Julian P.
AU - Revach, Guy
AU - Shlezinger, Nir
AU - Routtenberg, Tirza
AU - van Sloun, Ruud J.G.
PY - 2024/2
Y1 - 2024/2
N2 - Direction of arrival (DoA) estimation of multiple signals is pivotal in
sensor array signal processing. A popular multisignal DoA estimation
method is the multiple signal classification (MUSIC) algorithm, which
enables high-performance superresolution DoA recovery while being highly
applicable in practice. MUSIC is a model-based algorithm, relying on an
accurate mathematical description of the relationship between the
signals and the measurements and assumptions on the signals themselves
(non-coherent, narrowband sources). As such, it is sensitive to model
imperfections. In this work, we propose to overcome these limitations of
MUSIC by augmenting the algorithm with specifically designed neural
architectures. Our proposed deep augmented MUSIC (DA-MUSIC) algorithm is
thus a hybrid model-based/data-driven DoA estimator, which leverages
data to improve performance and robustness while preserving the
interpretable flow of the classic method. DA-MUSIC is shown to learn to
overcome limitations of the purely model-based method, such as its
inability to successfully localize coherent sources as well as estimate
the number of coherent signal sources present. We further demonstrate
the superior resolution of the DA-MUSIC algorithm in synthetic
narrowband and broadband scenarios as well as with real-world data of
DoA estimation from seismic signals
AB - Direction of arrival (DoA) estimation of multiple signals is pivotal in
sensor array signal processing. A popular multisignal DoA estimation
method is the multiple signal classification (MUSIC) algorithm, which
enables high-performance superresolution DoA recovery while being highly
applicable in practice. MUSIC is a model-based algorithm, relying on an
accurate mathematical description of the relationship between the
signals and the measurements and assumptions on the signals themselves
(non-coherent, narrowband sources). As such, it is sensitive to model
imperfections. In this work, we propose to overcome these limitations of
MUSIC by augmenting the algorithm with specifically designed neural
architectures. Our proposed deep augmented MUSIC (DA-MUSIC) algorithm is
thus a hybrid model-based/data-driven DoA estimator, which leverages
data to improve performance and robustness while preserving the
interpretable flow of the classic method. DA-MUSIC is shown to learn to
overcome limitations of the purely model-based method, such as its
inability to successfully localize coherent sources as well as estimate
the number of coherent signal sources present. We further demonstrate
the superior resolution of the DA-MUSIC algorithm in synthetic
narrowband and broadband scenarios as well as with real-world data of
DoA estimation from seismic signals
KW - Broadband communication
KW - Covariance matrices
KW - Direction-of-arrival estimation
KW - Estimation
KW - Multiple signal classification
KW - Narrowband
KW - Signal processing algorithms
KW - MUSIC
KW - DoA estimation
KW - model-based deep learning
UR - http://www.scopus.com/inward/record.url?scp=85172995604&partnerID=8YFLogxK
U2 - 10.1109/TVT.2023.3320360
DO - 10.1109/TVT.2023.3320360
M3 - Article
AN - SCOPUS:85172995604
SN - 0018-9545
VL - 73
SP - 2771
EP - 2785
JO - IEEE Transactions on Vehicular Technology
JF - IEEE Transactions on Vehicular Technology
IS - 2
M1 - 10266765
ER -