{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T05:49:53Z","timestamp":1769320193302,"version":"3.49.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T00:00:00Z","timestamp":1755648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Marine engineering has boomed and many deep learning-based methods have been proposed for underwater acoustic target recognition. However, most of these methods are dedicated to develop more complex convolutional neural networks to achieve better performance. This results in these models being unable to be deployed to low cost and miniaturized automatic underwater vehicles. A novel lightweight attentional residual neural network with data augmentation and feature fusion is proposed in this paper. Mel Frequency Cepstral Coefficient (MFCC), delta-MFCC and delta\u2013delta MFCC features are extracted in the time dimension for fusion to obtain the fusion feature. The SpecAugment data augmentation is also used to enhance the randomness and diversity of features by masking in time and frequency dimensions randomly. Shuffle attention in the residual blocks is introduced to enhance the representation of features. The lightweight model is evaluated and compared by using several metrics on ShipsEar and DeepShip datasets. The proposed lightweight model only requires 1.628\u00a0M parameters for the trained model. This work shows that the proposed method requires small memory storage, while it achieved comparative performance.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf099","type":"journal-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T11:26:18Z","timestamp":1754220378000},"page":"63-73","source":"Crossref","is-referenced-by-count":0,"title":["Clairaudience: a lightweight attentional residual neural network with data augmentation and feature fusion for underwater acoustic target recognition"],"prefix":"10.1093","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8482-4047","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4792-4884","authenticated-orcid":false,"given":"Yucheng","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1946-5454","authenticated-orcid":false,"given":"Xudong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3614-8722","authenticated-orcid":false,"given":"Xinglong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1980-1858","authenticated-orcid":false,"given":"Lili","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-8413","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8972-5208","authenticated-orcid":false,"given":"Pei","family":"Yu","sequence":"additional","affiliation":[{"name":"China Fire and Rescue Institute , Beijing 102202 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1751-8622","authenticated-orcid":false,"given":"Hongxin","family":"Tan","sequence":"additional","affiliation":[{"name":"Science and Technology on Complex Aviation Systems Simulation Laboratory , Beijing 100076 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2211-0059","authenticated-orcid":false,"given":"Kang","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Petrochemical Technology , Beijing 102617 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,8,20]]},"reference":[{"key":"2026011907114183900_ref1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/jmse11010003","article-title":"Deep learning-based classification of raw hydroacoustic signal: a review","volume":"11","author":"Lin","year":"2022","journal-title":"J Marine Sci Engineer"},{"key":"2026011907114183900_ref2","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.oceaneng.2019.04.011","article-title":"Advancements in the field of autonomous underwater vehicle","volume":"181","author":"Sahoo","year":"2019","journal-title":"Ocean Eng"},{"key":"2026011907114183900_ref3","doi-asserted-by":"publisher","first-page":"2265","DOI":"10.1121\/1.4900181","article-title":"The classification of underwater acoustic target signals based on wave structure and support vector machine","volume":"136","author":"Meng","year":"2024","journal-title":"J Acoust Soc Am"},{"key":"2026011907114183900_ref4","doi-asserted-by":"publisher","first-page":"102422","DOI":"10.1016\/j.inffus.2024.102422","article-title":"Automatic speech recognition using advanced deep learning approaches: a survey","volume":"109","author":"Kheddar","year":"2024","journal-title":"Information Fusion"},{"key":"2026011907114183900_ref5","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.isprsjprs.2023.12.012","article-title":"Remote sensing image classification using an ensemble framework without multiple classifiers","volume":"208","author":"Dou","year":"2024","journal-title":"ISPRS J Photogrammetr Remote Sens"},{"key":"2026011907114183900_ref6","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.3390\/s23041990","article-title":"Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: a review","volume":"23","author":"Er","year":"2023","journal-title":"Sensors"},{"key":"2026011907114183900_ref7","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.3390\/electronics9111972","article-title":"A review on deep learning-based approaches for automatic sonar target recognition","volume":"9","author":"Neupane","year":"2020","journal-title":"Electronics"},{"key":"2026011907114183900_ref8","first-page":"770","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. Nice, France, 18-20 Nonember","author":"He","year":"2016"},{"key":"2026011907114183900_ref9","doi-asserted-by":"publisher","first-page":"04011","DOI":"10.1051\/matecconf\/201928304011","article-title":"Underwater target recognition method based on convolution residual network","volume":"283","author":"Chen","year":"2019","journal-title":"EDP Sciences"},{"key":"2026011907114183900_ref10","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.3390\/jmse9111246","article-title":"An underwater acoustic target recognition method based on spectrograms with different resolutions","volume":"9","author":"Luo","year":"2021","journal-title":"J Mar Sci Eng"},{"key":"2026011907114183900_ref11","first-page":"1240","volume-title":"2021 IEEE 4th International Conference on Electronics Technology (ICET). Chengdu, China, 7-10 May","author":"Hong","year":"2021"},{"key":"2026011907114183900_ref12","doi-asserted-by":"publisher","first-page":"5492","DOI":"10.3390\/s22155492","article-title":"A novel deep-learning method with channel attention mechanism for underwater target recognition","volume":"22","author":"Xue","year":"2022","journal-title":"Sensors"},{"key":"2026011907114183900_ref13","doi-asserted-by":"publisher","first-page":"121235","DOI":"10.1016\/j.eswa.2023.121235","article-title":"A light-weight neural network for marine acoustic signal recognition suitable for fiber-optic hydrophones","volume":"235","author":"Lyu","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"2026011907114183900_ref14","doi-asserted-by":"publisher","first-page":"3333","DOI":"10.3390\/rs16173333","article-title":"Artificial intelligence-based underwater acoustic target recognition: a survey","volume":"16","author":"Feng","year":"2024","journal-title":"Remote Sens"},{"key":"2026011907114183900_ref15","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.3390\/rs15082068","article-title":"A fine-grained ship-radiated noise recognition system using deep hybrid neural networks with multi-scale features","volume":"15","author":"Liu","year":"2023","journal-title":"Remote Sens"},{"key":"2026011907114183900_ref16","doi-asserted-by":"publisher","first-page":"7297","DOI":"10.1007\/s11042-024-19178-9","article-title":"Underwater target recognition based on adaptive multi-feature fusion network","volume":"84","author":"Pan","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"2026011907114183900_ref17","doi-asserted-by":"publisher","first-page":"107989","DOI":"10.1016\/j.apacoust.2021.107989","article-title":"Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation","volume":"178","author":"Liu","year":"2021","journal-title":"Appl Acoust"},{"key":"2026011907114183900_ref18","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.3390\/rs11161888","article-title":"Underwater acoustic target recognition: a combination of multi-dimensional fusion features and modified deep neural network","volume":"11","author":"Wang","year":"2019","journal-title":"Remote Sens"},{"key":"2026011907114183900_ref19","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.3390\/app11041442","article-title":"Underwater acoustic target recognition with a residual network and the optimized feature extraction method","volume":"11","author":"Hong","year":"2021","journal-title":"Appl Sci"},{"key":"2026011907114183900_ref20","doi-asserted-by":"publisher","first-page":"e0266425","DOI":"10.1371\/journal.pone.0266425","article-title":"Underwater acoustic target recognition method based on a joint neural network","volume":"17","author":"Han","year":"2022","journal-title":"PloS One"},{"key":"2026011907114183900_ref21","doi-asserted-by":"publisher","first-page":"263","DOI":"10.3390\/jmse11020263","article-title":"VFR: the underwater acoustic target recognition using cross-domain pre-training with fbank fusion features","volume":"11","author":"Wu","year":"2023","journal-title":"J Mar Sci Eng"},{"key":"2026011907114183900_ref22","doi-asserted-by":"publisher","first-page":"107983","DOI":"10.1016\/j.engappai.2024.107983","article-title":"Underwater acoustic target recognition based on sub-band concatenated Mel spectrogram and multidomain attention mechanism","volume":"133","author":"Yang","year":"2024","journal-title":"Eng Appl Artif Intel"},{"key":"2026011907114183900_ref23","doi-asserted-by":"publisher","first-page":"432","DOI":"10.3390\/jmse11020432","article-title":"A lightweight network model based on an attention mechanism for ship-radiated noise classification","volume":"11","author":"Yang","year":"2023","journal-title":"J Mar Sci Eng"},{"key":"2026011907114183900_ref24","doi-asserted-by":"publisher","first-page":"115863","DOI":"10.1016\/j.oceaneng.2023.115863","article-title":"Differential treatment for time and frequency dimensions in mel-spectrograms: an efficient 3D spectrogram network for underwater acoustic target classification","volume":"287","author":"Tang","year":"2023","journal-title":"Ocean Eng"},{"key":"2026011907114183900_ref25","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3390\/jmse12010024","article-title":"Model for underwater acoustic target recognition with attention mechanism based on residual concatenate","volume":"12","author":"Chen","year":"2023","journal-title":"J Mar Sci Eng"},{"key":"2026011907114183900_ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680","article-title":"Specaugment: a simple data augmentation method for automatic speech recognition","volume-title":"Proc Interspeech","author":"Park"},{"key":"2026011907114183900_ref27","first-page":"2235","volume-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, 06-11 June","author":"Zhang","year":"2021"},{"key":"2026011907114183900_ref28","doi-asserted-by":"publisher","first-page":"8015","DOI":"10.1007\/s11042-024-19253-1","article-title":"MFCC in audio signal processing for voice disorder: a review","volume":"84","author":"Sidhu","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"2026011907114183900_ref29","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11760-023-02716-7","article-title":"Speech emotion recognition using mfcc-based entropy feature","volume":"18","author":"Mishra","year":"2024","journal-title":"Signal, image and video processing"},{"key":"2026011907114183900_ref30","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"2026011907114183900_ref31","doi-asserted-by":"publisher","first-page":"115270","DOI":"10.1016\/j.eswa.2021.115270","article-title":"DeepShip: an underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification","volume":"183","author":"Irfan","year":"2021","journal-title":"Expert Syst Appl"},{"key":"2026011907114183900_ref32","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.apacoust.2016.06.008","article-title":"ShipsEar: An underwater vessel noise database","volume":"113","author":"Santos-Dom\u00ednguez","year":"2016","journal-title":"Appl Acoust"},{"key":"2026011907114183900_ref33","article-title":"Adam: a method for stochastic optimization","volume-title":"Proc. 3rd Int Conf Learn Repres (ICLR)","author":"Kingma"},{"key":"2026011907114183900_ref34","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2026011907114183900_ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110119","article-title":"Joint learning model for underwater acoustic target recognition","volume":"260","author":"Tian","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"2026011907114183900_ref36","doi-asserted-by":"publisher","first-page":"589","DOI":"10.3390\/jmse12040589","article-title":"Mobile_ViT: underwater acoustic target recognition method based on local\u2013global feature fusion","volume":"12","author":"Yao","year":"2024","journal-title":"J Mar Sci Eng"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/1\/63\/64089122\/bxaf099.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/1\/63\/64089122\/bxaf099.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T12:11:50Z","timestamp":1768824710000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/1\/63\/8238529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,20]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,8,20]]},"published-print":{"date-parts":[[2026,1,13]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf099","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,8,20]]}}}