The reconstruction of sound sources by using inverse methods is known to be prone to estimation errors due to measurement noise, model mismatch, and poor conditioning of the inverse problem. This paper introduces a solution to map the estimation errors together with the reconstructed sound sources. From a Bayesian perspective, it initializes a Gibbs sampler with the Bayesian focusing method. The proposed Gibbs sampler is shown to converge within a few iterations, which makes it realistic for practical purposes. It also turns out to be very flexible in various scenarios. One peculiarity is the capability to directly operate on the cross-spectral matrix. Another one is to easily accommodate sparse priors. Eventually, it can also account for uncertainties in the microphone positions, which reinforces the regularization of the inverse problem.
References
1.
P. C.
Hansen
, Rank-Deficient and Discrete Ill-Posed Problems: Numerical Aspects of Linear Inversion
(Society for Industrial and Applied Mathematics
, Philadelphia, PA
, 1998
).2.
A.
Tarantola
, Inverse Problem Theory and Methods for Model Parameter Estimation
(Society for Industrial and Applied Mathematics
, Philadelphia, PA
, 2004
).3.
J.
Dettmer
, S. E.
Dosso
, and J. C.
Osler
, “Bayesian evidence computation for model selection in non-linear geoacoustic inference problems
,” J. Acoust. Soc. Am.
128
(6
), 3406
–3415
(2010
).4.
W.
Sanders
, “Estimation of error bounds in geoacoustic inversions
,” J. Acoust. Soc. Am.
113
(4
), 2191
–2191
(2003
).5.
S. E.
Dosso
, H.
Dong
, and K.
Duffaut
, “Model selection for profile structure in Bayesian geoacoustic inversion
,” J. Acoust. Soc. Am.
141
(5
), 3470
–3470
(2017
).6.
M.
Blau
, “Indirect measurement of multiple excitation force spectra by FRF matrix inversion: Influence of errors in statistical estimates of FRFs and response spectra
,” Acustica
85
(4
), 464
–479
(1999
).7.
E.
Zhang
, J.
Antoni
, and P.
Feissel
, “Bayesian force reconstruction with an uncertain model
,” J. Sound Vib.
331
(4
), 798
–814
(2012
).8.
K. R.
James
and D. R.
Dowling
, “A probability density function method for acoustic field uncertainty analysis
,” J. Acoust. Soc. Am.
118
(5
), 2802
–2810
(2005
).9.
D.
Battle
, “Applications of Markov chain Monte Carlo methods in ocean acoustics
,” J. Acoust. Soc. Am.
119
(5
), 3343
–3343
(2006
).10.
S. E.
Dosso
, “Bayesian inversion methods in ocean geoacoustics
,” J. Acoust. Soc. Am.
121
(5
), 3170
–3171
(2007
).11.
S. E.
Dosso
and M. J.
Wilmut
, “Bayesian source tracking in an uncertain ocean environment
,” J. Acoust. Soc. Am.
125
(4
), 2730
–2730
(2009
).12.
S. E.
Dosso
, “Bayesian localization, tracking, and environmental inference
,” J. Acoust. Soc. Am.
139
(4
), 2194
–2195
(2016
).13.
Z.
Michalopoulou
, “A Gibbs sampling approach to matched-field source localization and deconvolution
,” J. Acoust. Soc. Am.
108
(5
), 2646
–2646
(2000
).14.
P. L.
Nielsen
and S. E.
Dosso
, “Bayesian inversion of propagation and reverberation data
,” J. Acoust. Soc. Am.
120
(5
), 3356
–3356
(2006
).15.
Z.-H.
Michalopoulou
, “Multiple source localization using a maximum a posteriori Gibbs sampling approach
,” J. Acoust. Soc. Am.
120
(5
), 2627
–2634
(2006
).16.
M. Q.
Wu
and M. J.
Crocker
, “A statistical analysis of the estimation error of sound power measured by sound intensity techniques
,” J. Acoust. Soc. Am.
80
(S1
), S119
–S119
(1986
).17.
T.
Loyau
and J.
Pascal
, “Statistical errors in the estimation of the magnitude and direction of the complex acoustic intensity vector
,” J. Acoust. Soc. Am.
97
(5
), 2942
–2962
(1995
).18.
J.
Ghan
, B.
Cazzolato
, and S.
Snyder
, “Statistical errors in the estimation of time-averaged acoustic energy density using the two-microphone method
,” J. Acoust. Soc. Am.
115
(3
), 1179
–1184
(2004
).19.
M. R.
Bai
, J.-G.
Ih
, and J.
Benesty
, Acoustic Array Systems: Theory, Implementation, and Application
, 1st ed. (Wiley-IEEE Press
, New York
, 2013
).20.
G. P.
Carroll
, “The effect of sensor placement errors on cylindrical near-field acoustic holography
,” J. Acoust. Soc. Am.
105
(4
), 2269
–2276
(1999
).21.
A. W.
van der Vaart
, Asymptotic Statistics, in Cambridge Series in Statistical and Probabilistic Mathematics
(Cambridge University Press
, Cambridge
, 1998
), pp. 25
–34
.22.
J. A.
Scales
and L.
Tenorio
, “Prior information and uncertainty in inverse problems
,” Geophysics
66
, 389
(2001
).23.
A. M.
Stuart
, “Inverse problems: A Bayesian perspective
,” Acta Numerica
19
, 451
–559
(2010
).24.
J.
Antoni
, “A Bayesian approach to sound source reconstruction: Optimal basis, regularization, and focusing
,” J. Acoust. Soc. Am.
131
(4
), 2873
–2890
(2012
).25.
A.
Pereira
, Q.
Leclère
, and J.
Antoni
, “A theoretical and experimental comparison of the equivalent source method and a Bayesian approach to noise source identification
,” in Proceedings of Berlin Beamforming Conference
, Berlin (2012
), pp. 1
–12
.26.
A.
Gelman
, J. B.
Carlin
, H. S.
Stern
, and D. B.
Rubin
, Bayesian Data Analysis
, 2nd ed. (Chapman and Hall/CRC
, New York
, 2004
).27.
S.
Brooks
, A.
Gelman
, G.
Jones
, and X.-L.
Meng
, Handbook of Markov Chain Monte Carlo
(CRC
, Boca Raton, FL
, 2011
).28.
S. E.
Dosso
, “Quantifying uncertainty in geoacoustic inversion. I. A fast Gibbs sampler approach
,” J. Acoust. Soc. Am.
111
(1
), 129
–142
(2002
).29.
S. E.
Dosso
and P. L.
Nielsen
, “Quantifying uncertainty in geoacoustic inversion. II. Application to broadband, shallow-water data
,” J. Acoust. Soc. Am.
111
(1
), 143
–159
(2002
).30.
C.
Huang
, P.
Gerstoft
, and W. S.
Hodgkiss
, “Influence of data uncertainty on matched-field geoacoustic inversion
,” J. Acoust. Soc. Am.
115
(5
), 2409
–2409
(2004
).31.
R. T.
Muehleisen
, “Use of the Monte Carlo method for uncertainty analysis of acoustic models and measurements
,” J. Acoust. Soc. Am.
118
(3
), 1890
–1890
(2005
).32.
S. E.
Dosso
and M. J.
Wilmut
, “Uncertainty estimation in simultaneous Bayesian tracking and environmental inversion
,” J. Acoust. Soc. Am.
124
(1
), 82
–97
(2008
).33.
E.
Zhang
, J.
Antoni
, B.
Dong
, and H.
Snoussi
, “Bayesian space-frequency separation of wide-band sound sources by a hierarchical approach
,” J. Acoust. Soc. Am.
132
(5
), 3240
–3250
(2012
).34.
M. R.
Bai
, A.
Agarwal
, C.-C.
Chen
, and Y.-C.
Wang
, “Bayesian approach of nearfield acoustic reconstruction with particle filters
,” J. Acoust. Soc. Am.
133
(6
), 4032
–4043
(2013
).35.
J.
Antoni
, T. L.
Magueresse
, Q.
Leclére
, and P.
Simard
, “Sparse acoustical holography from iterated Bayesian focusing
,” J. Sound Vib.
446
, 289
–325
(2019
).36.
M. E.
Tipping
, “Sparse Bayesian learning and the relevance vector machine
,” J. Mach. Learn. Res.
1
, 211
–244
(2001
).37.
M. S.
Brandstein
, J. E.
Adcock
, and H. F.
Silverman
, “Microphone–array localization error estimation with application to sensor placement
,” J. Acoust. Soc. Am.
99
(6
), 3807
–3816
(1996
).38.
D. R.
Brillinger
, Time Series: Data Analysis and Theory
(Holt, Rinehart & Winston
, New York
, 1975
).39.
H.
Gzyl
, The Method of Maximum Entropy
, Vol. 29
of Series on Advances in Mathematics for Applied Sciences (World Scientific
, Singapore
, 1995
).40.
S.
Höhna
, T. A.
Heath
, B.
Boussau
, M. J.
Landis
, F.
Ronquist
, and J. P.
Huelsenbeck
, “Probabilistic graphical model representation in phylogenetics
,” Syst. Biol.
63
(5
), 753
–771
(2014
).41.
R. A.
Levine
and G.
Casella
, “Optimizing random scan Gibbs samplers
,” J. Multivar. Anal.
97
(10
), 2071
–2100
(2006
).42.
N. R.
Goodman
, “The distribution of the determinant of a complex Wishart distributed matrix
,” Ann. Math. Statist.
34
(1
), 178
–180
(1963
).43.
M. S.
Bartlett
, “XX.—On the theory of statistical regression
,” Proc. R. Soc. Edinburgh
53
, 260
–283
(1934
).44.
X.
Wang
, B.
Quost
, J.-D.
Chazot
, and J.
Antoni
, “Estimation of multiple sound sources with data and model uncertainties using the EM and evidential EM algorithms
,” Mech. Syst. Sign. Process.
66-67
, 159
–177
(2016
).45.
L.
Gilquin
, S.
Bouley
, J.
Antoni
, T. L.
Magueresse
, and C.
Marteau
, “Sensitivity analysis of two inverse methods: Conventional beamforming and Bayesian focusing
,” J. Sound Vib.
455
, 188
–202
(2019
).46.
D. E.
Johnson
and V.
Hegemann
, “Procedures to generate random matrices with noncentral distributions
,” Commun. Stat.
3
(7
), 691
–699
(1974
).47.
D. V.
Lindley
, Introduction to Probability and Statistics from a Bayesian Viewpoint
(Cambridge University Press
, Cambridge
, 1965
).48.
49.
S.
Roweis
, “Gaussian identities
,” https://cs.nyu.edu/∼roweis/notes/gaussid.pdf (Last viewed 08/07/2019).© 2019 Acoustical Society of America.
2019
Acoustical Society of America
You do not currently have access to this content.
