{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T03:57:56Z","timestamp":1778644676569,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10489-024-06035-3","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T04:17:40Z","timestamp":1733804260000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Echo lite voice fusion network: advancing underwater acoustic voiceprint recognition with lightweight neural architectures"],"prefix":"10.1007","volume":"55","author":[{"given":"Jiaqi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghai","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"6035_CR1","unstructured":"Urick RJ (1983) Principles of Underwater Sound; McGraw-Hill Book Co: Los Angeles. CA, USA, p 423p"},{"key":"6035_CR2","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/S1054-3139(03)00006-7","volume":"60","author":"AJ Kenny","year":"2003","unstructured":"Kenny AJ, Cato I, Desprez M, Fader G, Sch\u00fcttenhelm RTE, Side J (2003) An overview of seabed-mapping technologies in the context of marine habitat classification. ICES J Mar Sci 60:411\u2013418","journal-title":"ICES J Mar Sci"},{"key":"6035_CR3","doi-asserted-by":"publisher","first-page":"2776","DOI":"10.1109\/TMC.2020.3044397","volume":"21","author":"A Testolin","year":"2022","unstructured":"Testolin A, Kipnis D, Diamant R (2022) Detecting submerged objects using active acoustics and deep neural networks: a test case for pelagic fish. IEEE Trans Mob Comput 21:2776\u20132788","journal-title":"IEEE Trans Mob Comput"},{"key":"6035_CR4","doi-asserted-by":"publisher","first-page":"2945","DOI":"10.3390\/s20102945","volume":"20","author":"A Testolin","year":"2020","unstructured":"Testolin A, Diamant R (2020) Combining denoising autoencoders and dynamic programming for acoustic detection and tracking of underwater moving targets. Sensors 20:2945","journal-title":"Sensors"},{"key":"6035_CR5","doi-asserted-by":"publisher","first-page":"380","DOI":"10.3390\/jmse7110380","volume":"7","author":"F Yuan","year":"2019","unstructured":"Yuan F, Ke X, Cheng E (2019) Joint representation and recognition for ship-radiated noise based on multimodal deep learning. J Mar Sci Eng 7:380","journal-title":"J Mar Sci Eng"},{"issue":"04","key":"6035_CR6","doi-asserted-by":"publisher","first-page":"2242","DOI":"10.1121\/1.4920186","volume":"137","author":"Q Meng","year":"2015","unstructured":"Meng Q, Yang S (2015) A wave structure based method for recognition of marine acoustic target signals[J]. J Acoust Soc Am 137(04):2242\u20132242","journal-title":"J Acoust Soc Am"},{"issue":"03","key":"6035_CR7","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1109\/72.846748","volume":"11","author":"MR Azimi-Sadjadi","year":"2000","unstructured":"Azimi-Sadjadi MR, Yao D, Huang Q et al (2000) Underwater target classification using wavelet packets and neural networks[J]. IEEE Trans Neural Netw 11(03):784\u2013794","journal-title":"IEEE Trans Neural Netw"},{"key":"6035_CR8","doi-asserted-by":"crossref","unstructured":"Kang C, Zhang X, Zhang A et al (2004) Underwater acoustic targets classification using welch spectrum estimation and neural networks[C]. Advances in neural networks-ISNN 2004: international symposium on neural networks. Dalian, China, pp 930\u2013935","DOI":"10.1007\/978-3-540-28647-9_153"},{"issue":"01","key":"6035_CR9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1049\/iet-rsn.2011.0142","volume":"7","author":"A Das","year":"2013","unstructured":"Das A, Kumar A, Bahl R (2013) Marine vessel classification based on passive sonar data: the cepstrum-based approach[J]. IET Radar, Sonar & Navigation 7(01):87\u201393","journal-title":"IET Radar, Sonar & Navigation"},{"key":"6035_CR10","first-page":"1","volume":"7864213","author":"L Zhang","year":"2016","unstructured":"Zhang L, Wu D, Han X et al (2016) Feature extraction of underwater target signal using mel frequency cepstrum coefficients based on acoustic vector sensor[J]. J Sens 7864213:1\u201311","journal-title":"J Sens"},{"key":"6035_CR11","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s11265-018-1347-x","volume":"91","author":"MS Jahromi","year":"2019","unstructured":"Jahromi MS, Bagheri V, Rostami H et al (2019) Feature extraction in fractional Fourier domain for classification of passive sonar signals[J]. J Signal Process Syst 91:511\u2013520","journal-title":"J Signal Process Syst"},{"key":"6035_CR12","doi-asserted-by":"crossref","unstructured":"Mohankumar K, Supriya MH, Pillai PR (2015) Bispectral gammatone cepstral coefficient based neural network classifier[C]. In: 2015 IEEE underwater technology, Chennai, India, 2015, pp 1\u20135","DOI":"10.1109\/UT.2015.7108321"},{"issue":"06","key":"6035_CR13","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.1109\/TGRS.2016.2522972","volume":"54","author":"M Tuma","year":"2016","unstructured":"Tuma M, R\u00f8rbech V, Prior MK et al (2016) Integrated optimization of long-range underwater signal detection, feature extraction, and classification for nuclear treaty monitoring[J]. IEEE Trans Geosci Remote Sens 54(06):3649\u20133659","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"6035_CR14","doi-asserted-by":"publisher","first-page":"107057","DOI":"10.1016\/j.apacoust.2019.107057","volume":"159","author":"X Ke","year":"2020","unstructured":"Ke X, Yuan F, Cheng E (2020) Integrated optimization of underwater acoustic ship-radiated noise recognition based on two-dimensional feature fusion[J]. Appl Acoust 159:107057","journal-title":"Appl Acoust"},{"key":"6035_CR15","doi-asserted-by":"crossref","unstructured":"Yang H, Gan A, Chen H et al (2016) Underwater acoustic target recognition using SVM ensemble via weighted sample and feature selection[C]. 2016 13th International Bhurban conference on applied sciences and technology. Islamabad, Pakistan, pp 522\u2013527","DOI":"10.1109\/IBCAST.2016.7429928"},{"issue":"06","key":"6035_CR16","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1049\/iet-rsn.2010.0157","volume":"5","author":"WS Filho","year":"2011","unstructured":"Filho WS, Seixas JM, Moura NN (2011) Preprocessing passive sonar signals for neural classification[J]. IET Radar, Sonar & Navigation 5(06):605\u2013612","journal-title":"IET Radar, Sonar & Navigation"},{"issue":"6","key":"6035_CR17","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.3390\/s22062181","volume":"22","author":"LC Domingos","year":"2022","unstructured":"Domingos LC, Santos PE, Skelton PS et al (2022) A survey of underwater acoustic data classification methods using deep learning for shoreline surveillance[J]. Sensors 22(6):2181","journal-title":"Sensors"},{"issue":"2","key":"6035_CR18","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.dt.2012.09.001","volume":"9","author":"X-Y Zeng","year":"2013","unstructured":"Zeng X-Y, Wang S-G (2013) Bark-wavelet analysis and Hilbert-Huang transform for underwater target recognition. Def Technol 9(2):115\u2013120","journal-title":"Def Technol"},{"key":"6035_CR19","doi-asserted-by":"crossref","unstructured":"ksuren IG, Hocaoglu AK (2022) Automatic Target Classification Using Underwater Acoustic Signals. In Proceedings of the 2022 30th signal processing and communications applications conference (SIU). Safranbolu, Turkey, 15\u201318","DOI":"10.1109\/SIU55565.2022.9864771"},{"key":"6035_CR20","doi-asserted-by":"crossref","unstructured":"Wang P, Peng Y (2020) Research on feature extraction and recognition method of underwater acoustic target based on deep convolutional network. In: Proceedings of the 2020 IEEE international conference on advances in electrical engineering and computer applications (AEECA). Dalian, China, 25\u201327, pp 863\u2013868","DOI":"10.1109\/AEECA49918.2020.9213504"},{"key":"6035_CR21","first-page":"372","volume":"33","author":"S Chao-xion","year":"2014","unstructured":"Chao-xion S (2014) Application of the lifting wavelet transform based MFCC in target identification. Tech Acoust 33:372\u2013375","journal-title":"Tech Acoust"},{"key":"6035_CR22","doi-asserted-by":"publisher","first-page":"172988142097630","DOI":"10.1177\/1729881420976307","volume":"17","author":"B Teng","year":"2020","unstructured":"Teng B, Zhao H (2020) Underwater target recognition methods based on the framework of deep learning: a survey. Int J Adv Robot Syst 17:172988142097630","journal-title":"Int J Adv Robot Syst"},{"key":"6035_CR23","doi-asserted-by":"publisher","first-page":"108261","DOI":"10.1016\/j.apacoust.2021.108261","volume":"182","author":"Q Zhang","year":"2021","unstructured":"Zhang Q, Da L, Zhang Y, Hu Y (2021) Integrated neural networks based on feature fusion for underwater target recognition. Appl Acoust 182:108261","journal-title":"Appl Acoust"},{"key":"6035_CR24","doi-asserted-by":"publisher","unstructured":"Desplanques B et al (2020) ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. Interspeech 2020, https:\/\/doi.org\/10.21437\/interspeech.2020-2650","DOI":"10.21437\/interspeech.2020-2650"},{"key":"6035_CR25","doi-asserted-by":"crossref","unstructured":"Hu J et al (2018) Squeeze-and-Excitation Networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00745"},{"key":"6035_CR26","doi-asserted-by":"crossref","unstructured":"Wang H et al (2023) CAM++: a fast and efficient network for speaker verification using context-aware masking","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"6035_CR27","doi-asserted-by":"crossref","unstructured":"Yu Y-Q, Li W-J (2020) Densely connected time delay neural network for speaker verification. Interspeech","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"6035_CR28","doi-asserted-by":"crossref","unstructured":"Choudhary S et al (2022) LEAN: light and efficient audio classification network. In: 2022 IEEE 19th india council international conference (INDICON). IEEE","DOI":"10.1109\/INDICON56171.2022.10039921"},{"key":"6035_CR29","doi-asserted-by":"crossref","unstructured":"Chen Y et al (2023) Effective audio classification network based on paired inverse pyramid structure and dense mlp block. In: Huang, DS, Premaratne P, Jin B, Qu B, Jo KH, Hussain A (eds) Advanced intelligent computing technology and applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore","DOI":"10.1007\/978-981-99-4742-3_6"},{"key":"6035_CR30","doi-asserted-by":"publisher","unstructured":"Jena KK et al (2023) A hybrid deep learning approach for classification of music genres using wavelet and spectrogram analysis. Neural Computing and Applications, pp 11223\u201348. https:\/\/doi.org\/10.1007\/s00521-023-08294-6","DOI":"10.1007\/s00521-023-08294-6"},{"key":"6035_CR31","doi-asserted-by":"crossref","unstructured":"Liu X et al (2023) Cat: Causal audio transformer for audio classification. In: ICASSP 2023-2023 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE","DOI":"10.1109\/ICASSP49357.2023.10096787"},{"key":"6035_CR32","doi-asserted-by":"crossref","unstructured":"Zhu W, Omar M (2023) Multiscale audio spectrogram transformer for efficient audio classification","DOI":"10.1109\/ICASSP49357.2023.10096513"},{"key":"6035_CR33","doi-asserted-by":"publisher","unstructured":"Howard A et al (2019) Searching for MobileNetV3. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), https:\/\/doi.org\/10.1109\/iccv.2019.00140","DOI":"10.1109\/iccv.2019.00140"},{"key":"6035_CR34","unstructured":"Ramachandran P, Zoph B, Le Q V (2017) Searching for activation functions[J]. arXiv:1710.05941"},{"key":"6035_CR35","doi-asserted-by":"publisher","unstructured":"Castro M, Mario A, et al (2022) Prediction of speech intelligibility with dnn-based performance measures. Computer Speech & amp; Language, pp 101329, https:\/\/doi.org\/10.1016\/j.csl.2021.101329","DOI":"10.1016\/j.csl.2021.101329"},{"key":"6035_CR36","doi-asserted-by":"crossref","unstructured":"Kong Q, et al (2021) PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"6035_CR37","doi-asserted-by":"crossref","unstructured":"Woo, Sanghyun, et al (2023) Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"6035_CR38","doi-asserted-by":"crossref","unstructured":"Touvron H, Cord M, J\u00e9gou H (2022) DeiT III: revenge of the ViT. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) ECCV. Springer, Cham, pp 516\u2013533","DOI":"10.1007\/978-3-031-20053-3_30"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06035-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-06035-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06035-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T15:06:29Z","timestamp":1737385589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-06035-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6035"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-06035-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"11 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing of Interest"}},{"value":"In this study, we used public benchmark dataset.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"112"}}