Underwater acoustic target recognition has emerged as a prominent research area within the field of underwater acoustics. However, the current availability of authentic underwater acoustic signal recordings remains limited, which hinders data-driven acoustic recognition models from learning robust patterns of targets from a limited set of intricate underwater signals, thereby compromising their stability in practical applications. To overcome these limitations, this study proposes a recognition framework called M3 (multitask, multi-gate, multi-expert) to enhance the model's ability to capture robust patterns by making it aware of the inherent properties of targets. In this framework, an auxiliary task that focuses on target properties, such as estimating target size, is designed. The auxiliary task then shares parameters with the recognition task to realize multitask learning. This paradigm allows the model to concentrate on shared information across tasks and identify robust patterns of targets in a regularized manner, thus, enhancing the model's generalization ability. Moreover, M3 incorporates multi-expert and multi-gate mechanisms, allowing for the allocation of distinct parameter spaces to various underwater signals. This enables the model to process intricate signal patterns in a fine-grained and differentiated manner. To evaluate the effectiveness of M3, extensive experiments were implemented on the ShipsEar underwater ship-radiated noise dataset. The results substantiate that M3 has the ability to outperform the most advanced single-task recognition models, thereby achieving the state-of-the-art performance.

1.
Akbarian
,
H.
, and
Sedaaghi
,
M. H.
(
2023
). “
Recognition of acoustic emitted from surface vessels using mobilenet convolutional algorithm
,”
Adv. Def. Sci. Technol.
1
,
39
50
.
2.
Caruana
,
R.
(
1997
). “
Multitask learning
,”
Mach. Learn.
28
,
41
75
.
3.
Erkmen
,
B.
, and
Yıldırım
,
T.
(
2008
). “
Improving classification performance of sonar targets by applying general regression neural network with PCA
,”
Expert Syst. Appl.
35
(
1-2
),
472
475
.
4.
Feng
,
H.
,
Chen
,
X.
,
Wang
,
R.
,
Wang
,
H.
,
Yao
,
H.
, and
Wu
,
F.
(
2024
). “
Underwater acoustic target recognition method based on WA-DS decision fusion
,”
Appl. Acoust.
217
,
109851
.
5.
Fillinger
,
L.
,
de Theije
,
P.
,
Zampolli
,
M.
,
Sutin
,
A.
,
Salloum
,
H.
,
Sedunov
,
N.
, and
Sedunov
,
A.
(
2010
). “
Towards a passive acoustic underwater system for protecting harbours against intruders
,” in
2010 International WaterSide Security Conference
, Carrara, Italy (November 3–5, 2010) (
IEEE
,
New York
), pp.
1
7
.
6.
Gerg
,
I. D.
,
Williams
,
D. P.
, and
Monga
,
V.
(
2020
). “
Data adaptive image enhancement and classification for synthetic aperture sonar
,” in
IGARSS 2020, 2020 IEEE International Geoscience and Remote Sensing Symposium
(September 26–October 2, 2020) (
IEEE
,
New York
), pp.
2835
2838
.
7.
Ha
,
D. V.
,
Nguyen
,
V. D.
, and
Nguyen
,
Q. K.
(
2017
). “
Modeling of doppler power spectrum for underwater acoustic channels
,”
J. Commun. Netw.
19
(
3
),
270
281
.
8.
Hazimeh
,
H.
,
Zhao
,
Z.
,
Chowdhery
,
A.
,
Sathiamoorthy
,
M.
,
Chen
,
Y.
,
Mazumder
,
R.
,
Hong
,
L.
, and
Chi
,
E.
(
2021
). “
DSelect-k: Differentiable selection in the mixture of experts with applications to multi-task learning
,”
Adv. Neural Inf. Process. Syst.
34
,
29335
29347
.
9.
He
,
K.
,
Zhang
,
X.
,
Ren
,
S.
, and
Sun
,
J.
(
2016
). “
Deep residual learning for image recognition
,” in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Las Vegas, NV (June 27–30, 2016) (
IEEE
,
New York
), pp.
770
778
.
10.
Hummel
,
H. I.
,
van der Mei
,
R.
, and
Bhulai
,
S.
(
2024
). “
A survey on machine learning in ship radiated noise
,”
Ocean Eng.
298
,
117252
.
11.
Irfan
,
M.
,
Jiangbin
,
Z.
,
Ali
,
S.
,
Iqbal
,
M.
,
Masood
,
Z.
, and
Hamid
,
U.
(
2021
). “
Deepship: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification
,”
Expert Syst. Appl.
183
,
115270
.
12.
Jacobs
,
R. A.
,
Jordan
,
M. I.
,
Nowlan
,
S. J.
, and
Hinton
,
G. E.
(
1991
). “
Adaptive mixtures of local experts
,”
Neural Comput.
3
(
1
),
79
87
.
13.
Ji
,
F.
,
Ni
,
J.
,
Li
,
G.
,
Liu
,
L.
, and
Wang
,
Y.
(
2023
). “
Underwater acoustic target recognition based on deep residual attention convolutional neural network
,”
J. Mar. Sci. Eng.
11
(
8
),
1626
.
14.
Jia
,
H.
,
Khishe
,
M.
,
Mohammadi
,
M.
, and
Rashidi
,
S.
(
2022
). “
Deep cepstrum-wavelet autoencoder: A novel intelligent sonar classifier
,”
Expert Syst. Appl.
202
,
117295
.
15.
Jiang
,
J.
,
Shi
,
T.
,
Huang
,
M.
, and
Xiao
,
Z.
(
2020
). “
Multi-scale spectral feature extraction for underwater acoustic target recognition
,”
Measurement
166
,
108227
.
16.
Jin
,
S.-Y.
,
Su
,
Y.
,
Guo
,
C.-J.
,
Fan
,
Y.-X.
, and
Tao
,
Z.-Y.
(
2023
). “
Offshore ship recognition based on center frequency projection of improved EMD and KNN algorithm
,”
Mech. Syst. Signal Process.
189
,
110076
.
17.
Kamalipour
,
M.
,
Agahi
,
H.
,
Khishe
,
M.
, and
Mahmoodzadeh
,
A.
(
2023
). “
Passive ship detection and classification using hybrid cepstrums and deep compound autoencoders
,”
Neural Comput. Applic.
35
(
10
),
7833
7851
.
18.
Kang
,
C.
,
Zhang
,
X.
,
Zhang
,
A.
, and
Lin
,
H.
(
2004
). “
Underwater acoustic targets classification using welch spectrum estimation and neural networks
,” in
International Symposium on Neural Networks
, Dalian, China (August 19–21, 2002) (
Springer
,
Berlin
), pp.
930
935
.
19.
Kendall
,
A.
,
Gal
,
Y.
, and
Cipolla
,
R.
(
2018
). “
Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
,” in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Salt Lake City, UT (June 18–22, 2018) (
IEEE
,
New York
), pp.
7482
7491
.
20.
Li
,
D.
,
Liu
,
F.
,
Shen
,
T.
,
Chen
,
L.
, and
Zhao
,
D.
(
2023a
). “
Data augmentation method for underwater acoustic target recognition based on underwater acoustic channel modeling and transfer learning
,”
Appl. Acoust.
208
,
109344
.
21.
Li
,
D.
,
Liu
,
F.
,
Shen
,
T.
,
Chen
,
L.
, and
Zhao
,
D.
(
2023b
). “
A robust feature extraction method for underwater acoustic target recognition based on multi-task learning
,”
Electronics
12
(
7
),
1708
.
22.
Li
,
J.
, and
Yang
,
H.
(
2021
). “
The underwater acoustic target timbre perception and recognition based on the auditory inspired deep convolutional neural network
,”
Appl. Acoust.
182
,
108210
.
23.
Li
,
L.
,
Song
,
S.
, and
Feng
,
X.
(
2022
). “
Combined LOFAR and DEMON spectrums for simultaneous underwater acoustic object counting and F0 estimation
,”
J. Mar. Sci. Eng.
10
(
10
),
1565
.
24.
Liang
,
Y.
,
Yu
,
H.
,
Ji
,
F.
, and
Chen
,
F.
(
2023
). “
Multitask sparse Bayesian channel estimation for turbo equalization in underwater acoustic communications
,”
IEEE J. Ocean. Eng.
48
(
3
),
946
962
.
25.
Liu
,
F.
,
Shen
,
T.
,
Luo
,
Z.
,
Zhao
,
D.
, and
Guo
,
S.
(
2021
). “
Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation
,”
Appl. Acoust.
178
,
107989
.
26.
Liu
,
Y.
,
Niu
,
H.
, and
Li
,
Z.
(
2020
). “
A multi-task learning convolutional neural network for source localization in deep ocean
,”
J. Acoust. Soc. Am.
148
(
2
),
873
883
.
27.
Loshchilov
,
I.
, and
Hutter
,
F.
(
2017
). “
Decoupled weight decay regularization
,” arXiv:1711.05101.
28.
Lu
,
J.
,
Song
,
S.
,
Hu
,
Z.
, and
Li
,
S.
(
2020
). “
Fundamental frequency detection of underwater acoustic target using demon spectrum and CNN network
,” in
2020 3rd International Conference on Unmanned Systems (ICUS)
, Harbin, China (November 27–28, 2020) (
IEEE
,
New York
), pp.
778
784
.
29.
Luo
,
X.
,
Feng
,
Y.
, and
Zhang
,
M.
(
2021a
). “
An underwater acoustic target recognition method based on combined feature with automatic coding and reconstruction
,”
IEEE Access
9
,
63841
63854
.
30.
Luo
,
X.
,
Zhang
,
M.
,
Liu
,
T.
,
Huang
,
M.
, and
Xu
,
X.
(
2021b
). “
An underwater acoustic target recognition method based on spectrograms with different resolutions
,”
J. Mar. Sci. Eng.
9
(
11
),
1246
.
31.
Ma
,
J.
,
Zhao
,
Z.
,
Yi
,
X.
,
Chen
,
J.
,
Hong
,
L.
, and
Chi
,
E. H.
(
2018
). “
Modeling task relationships in multi-task learning with multi-gate mixture-of-experts
,” in
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
, London, UK (August 19–23, 2018) (
ACM
,
New York
), pp.
1930
1939
.
32.
MacQueen
,
J.
(
1967
). “
Some methods for classification and analysis of multivariate observations
,” in
Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability
, Statistical Laboratory University of California (June 21–July 18, 1965 and December 27, 1965–January 7, 1966) (
University of California Press
,
Berkeley, CA
), Vol.
1
, pp.
281
297
.
33.
Misra
,
I.
,
Shrivastava
,
A.
,
Gupta
,
A.
, and
Hebert
,
M.
(
2016
). “
Cross-stitch networks for multi-task learning
,” in
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Las Vegas, NV (June 27–30, 2016) (
IEEE
,
New York
), pp.
3994
4003
.
34.
Neilsen
,
T.
,
Escobar-Amado
,
C.
,
Acree
,
M.
,
Hodgkiss
,
W.
,
Van Komen
,
D.
,
Knobles
,
D.
,
Badiey
,
M.
, and
Castro-Correa
,
J.
(
2021
). “
Learning location and seabed type from a moving mid-frequency source
,”
J. Acoust. Soc. Am.
149
(
1
),
692
705
.
35.
Niu
,
H.
,
Li
,
X.
,
Zhang
,
Y.
, and
Xu
,
J.
(
2023
). “
Advances and applications of machine learning in underwater acoustics
,”
Intell. Mar. Technol. Syst.
1
(
1
),
8
.
36.
Rajagopal
,
R.
,
Sankaranarayanan
,
B.
, and
Rao
,
P. R.
(
1990
). “
Target classification in a passive sonar—An expert system approach
,” in
International Conference on Acoustics, Speech, and Signal Processing
, Albuquerque, NM (April 3–6, 1990) (
IEEE
,
New York
), pp.
2911
2914
.
37.
Ren
,
J.
,
Xie
,
Y.
,
Zhang
,
X.
, and
Xu
,
J.
(
2022
). “
UALF: A learnable front-end for intelligent underwater acoustic classification system
,”
Ocean Eng.
264
,
112394
.
38.
Riquelme
,
C.
,
Puigcerver
,
J.
,
Mustafa
,
B.
,
Neumann
,
M.
,
Jenatton
,
R.
,
Susano Pinto
,
A.
,
Keysers
,
D.
, and
Houlsby
,
N.
(
2021
). “
Scaling vision with sparse mixture of experts
,”
Adv. Neural Inf. Process. Syst.
34
,
8583
8595
.
39.
Ruder
,
S.
(
2017
). “
An overview of multi-task learning in deep neural networks
,” arXiv:1706.05098.
40.
Ruder
,
S.
,
Bingel
,
J.
,
Augenstein
,
I.
, and
Søgaard
,
A.
(
2017
). “
Sluice networks: Learning what to share between loosely related tasks
,” arXiv:1705.08142.
41.
Santos-Domínguez
,
D.
,
Torres-Guijarro
,
S.
,
Cardenal-López
,
A.
, and
Pena-Gimenez
,
A.
(
2016
). “
Shipsear: An underwater vessel noise database
,”
Appl. Acoust.
113
,
64
69
.
42.
Sha'ameri
,
A. Z.
,
Al-Aboosi
,
Y. Y.
, and
Khamis
,
N. H. H.
(
2014
). “
Underwater acoustic noise characteristics of shallow water in tropical seas
,” in
2014 International Conference on Computer and Communication Engineering
, Kuala Lumpur, Malaysia (September 23–25, 2014) (
IEEE
,
New York
), pp.
80
83
.
43.
Shahapure
,
K. R.
, and
Nicholas
,
C.
(
2020
). “
Cluster quality analysis using silhouette score
,” in
2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA)
(October 6–9, 2020) (
IEEE
,
New York
), pp.
747
748
.
44.
Simonović
,
M.
,
Kovandžić
,
M.
,
Ćirić
,
I.
, and
Nikolić
,
V.
(
2021
). “
Acoustic recognition of noise-like environmental sounds by using artificial neural network
,”
Expert Syst. Appl.
184
,
115484
.
45.
Song
,
Y.
,
Wen
,
J.
,
Yu
,
D.
,
Liu
,
Y.
, and
Wen
,
X.
(
2014
). “
Reduction of vibration and noise radiation of an underwater vehicle due to propeller forces using periodically layered isolators
,”
J. Sound Vib.
333
(
14
),
3031
3043
.
46.
Stojanovic
,
M.
,
Catipovic
,
J.
, and
Proakis
,
J. G.
(
1993
). “
Adaptive multichannel combining and equalization for underwater acoustic communications
,”
J. Acoust. Soc. Am.
94
(
3
),
1621
1631
.
47.
Sutin
,
A.
,
Bunin
,
B.
,
Sedunov
,
A.
,
Sedunov
,
N.
,
Fillinger
,
L.
,
Tsionskiy
,
M.
, and
Bruno
,
M.
(
2010
). “
Stevens passive acoustic system for underwater surveillance
,” in
2010 International WaterSide Security Conference
, Marina di Carrara, Italy (November 3–5, 2010) (
IEEE
,
New York
), pp.
1
6
.
48.
Tang
,
H.
,
Liu
,
J.
,
Zhao
,
M.
, and
Gong
,
X.
(
2020
). “
Progressive layered extraction (PLE): A novel multi-task learning (MTL) model for personalized recommendations
,” in
Proceedings of the 14th ACM Conference on Recommender Systems
, Rio de Janeiro, Brazil (September 22–26, 2020) (
ACM
,
New York
), pp.
269
278
.
49.
Tang
,
N.
,
Zhou
,
F.
,
Wang
,
Y.
,
Zhang
,
H.
,
Lyu
,
T.
,
Wang
,
Z.
, and
Chang
,
L.
(
2023
). “
Differential treatment for time and frequency dimensions in Mel-spectrograms: An efficient 3D spectrogram network for underwater acoustic target classification
,”
Ocean Eng.
287
,
115863
.
50.
Vaccaro
,
R. J.
(
1998
). “
The past, present, and the future of underwater acoustic signal processing
,”
IEEE Signal Process. Mag.
15
(
4
),
21
51
.
51.
Van der Maaten
,
L.
, and
Hinton
,
G.
(
2008
). “
Visualizing data using t-SNE
,”
J. Mach. Learn. Res.
9
(
11
),
2579
2605
.
52.
Williams
,
D. P.
(
2019
). “
Transfer learning with SAS-image convolutional neural networks for improved underwater target classification
,” in
IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium
, Yokohama, Japan (July 28–August 2, 2019) (
IEEE
,
New York
), pp.
78
81
.
53.
Wu
,
Y.
,
Ayyalasomayajula
,
R.
,
Bianco
,
M. J.
,
Bharadia
,
D.
, and
Gerstoft
,
P.
(
2021
). “
Sound source localization based on multi-task learning and image translation network
,”
J. Acoust. Soc. Am.
150
(
5
),
3374
3386
.
54.
Xie
,
Y.
,
Chen
,
T.
, and
Xu
,
J.
(
2023a
). “
Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization
,” arXiv:2304.11907.
55.
Xie
,
Y.
,
Ren
,
J.
, and
Xu
,
J.
(
2022a
). “
Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform
,”
Ocean Eng.
265
,
112626
.
56.
Xie
,
Y.
,
Ren
,
J.
, and
Xu
,
J.
(
2022b
). “
Underwater-art: Expanding information perspectives with text templates for underwater acoustic target recognition
,”
J. Acoust. Soc. Am.
152
(
5
),
2641
2651
.
57.
Xie
,
Y.
,
Ren
,
J.
, and
Xu
,
J.
(
2023b
). “
Guiding the underwater acoustic target recognition with interpretable contrastive learning
,” in
OCEANS 2023
, Limerick, Ireland (June 5–8, 2023) (
IEEE/OES and Marine Technology Society
,
New York
), pp.
1
6
.
58.
Xie
,
Y.
,
Ren
,
J.
, and
Xu
,
J.
(
2024
). “
Unraveling complex data diversity in underwater acoustic target recognition through convolution-based mixture of experts
,”
Expert Syst. Appl.
249
,
123431
.
59.
Xu
,
J.
,
Xie
,
Y.
, and
Wang
,
W.
(
2023
). “
Underwater acoustic target recognition based on smoothness-inducing regularization and spectrogram-based data augmentation
,”
Ocean Eng.
281
,
114926
.
60.
Xue
,
L.
,
Zeng
,
X.
, and
Jin
,
A.
(
2022
). “
A novel deep-learning method with channel attention mechanism for underwater target recognition
,”
Sensors
22
(
15
),
5492
.
61.
Yang
,
H.
,
Gan
,
A.
,
Chen
,
H.
,
Pan
,
Y.
,
Tang
,
J.
, and
Li
,
J.
(
2016
). “
Underwater acoustic target recognition using SVM ensemble via weighted sample and feature selection
,” in
2016 13th International Bhurban Conference on Applied Sciences and Technology (IBCAST)
, Islamabad, Pakistan (January 12–16, 2016) (
IEEE
,
New York
), pp.
522
527
.
62.
Yang
,
S.
,
Xue
,
L.
,
Hong
,
X.
, and
Zeng
,
X.
(
2023
). “
A lightweight network model based on an attention mechanism for ship-radiated noise classification
,”
J. Mar. Sci. Eng.
11
(
2
),
432
.
63.
Yin
,
X.
,
Sun
,
X.
,
Liu
,
P.
,
Wang
,
L.
, and
Tang
,
R.
(
2020
). “
Underwater acoustic target classification based on LOFAR spectrum and convolutional neural network
,” in
Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture
, Manchester, UK (October 16–18, 2020), pp.
59
63
.
64.
Zeng
,
X.
,
Lu
,
C.
, and
Li
,
Y.
(
2020
). “
A multi-task sparse feature learning method for underwater acoustic target recognition based on two uniform linear hydrophone arrays
,” in
INTER-NOISE and NOISE-CON Congress and Conference Proceedings
, Seoul, South Korea (August 30–September 2, 2020) (
The Institute of Noise Control Engineering of the USA
,
Wakefield, MA
), Vol.
261
, pp.
4404
4411
.
65.
Zhang
,
Y.
,
Wang
,
H.
,
Li
,
C.
,
Chen
,
D.
, and
Meriaudeau
,
F.
(
2021
). “
Meta-learning-aided orthogonal frequency division multiplexing for underwater acoustic communications
,”
J. Acoust. Soc. Am.
149
(
6
),
4596
4606
.
66.
Zhang
,
Y.
,
Wang
,
H.
,
Li
,
C.
, and
Meriaudeau
,
F.
(
2022
). “
Complex-valued deep network aided channel tracking for underwater acoustic communications
,” in
OCEANS 2022
, Chennai, India (February 21–24, 2022) (
IEEE/OES and Marine Technology Society
,
New York
), pp.
1
5
.
67.
Zhou
,
A.
,
Zhang
,
W.
,
Li
,
X.
,
Xu
,
G.
,
Zhang
,
B.
,
Ma
,
Y.
, and
Song
,
J.
(
2023
). “
A novel noise-aware deep learning model for underwater acoustic denoising
,”
IEEE Trans. Geosci. Remote Sens.
61
,
4202813
.
68.
Zhou
,
X.
, and
Yang
,
K.
(
2020
). “
A denoising representation framework for underwater acoustic signal recognition
,”
J. Acoust. Soc. Am.
147
(
4
),
EL377
EL383
.
You do not currently have access to this content.