{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:26:34Z","timestamp":1757618794135,"version":"3.44.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2023NSFSC0470","2024ZDZX0004"],"award-info":[{"award-number":["2023NSFSC0470","2024ZDZX0004"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171387"],"award-info":[{"award-number":["62171387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xihua University Science and Technology Innovation Competition Project for Postgraduate Students","award":["YK20240140"],"award-info":[{"award-number":["YK20240140"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s40747-025-02017-1","type":"journal-article","created":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T09:00:58Z","timestamp":1752310858000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio copy-move forgery detection with decreasing convolutional kernel neural network and spectrogram fusion"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6294-3272","authenticated-orcid":false,"given":"Canghong","family":"Shi","sequence":"first","affiliation":[]},{"given":"Xin","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Min","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xianhua","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Xiaojie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Sani M.","family":"Abdullahi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"issue":"1","key":"2017_CR1","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1007\/s11042-016-4277-2","volume":"77","author":"KM Zakariah","year":"2018","unstructured":"Zakariah KM (2018) Digital multimedia audio forensics: past, present and future. Multimedia Tools Appl 77(1):1009\u20131040","journal-title":"Multimedia Tools Appl"},{"key":"2017_CR2","doi-asserted-by":"crossref","unstructured":"Bevinamarad PR, Shirldonkar MS (2020) Audio forgery detection techniques: present and past review. In: 2020 4th International conference on trends in electronics and informatics (ICOEI) (48184), pp 613\u2013618","DOI":"10.1109\/ICOEI48184.2020.9143014"},{"key":"2017_CR3","first-page":"78800","volume":"7880","author":"C Kraetzer","year":"2011","unstructured":"Kraetzer C, Memon ND, Dittmann J, Qian K, Schott M, Alattar AM, Delp Iii EJ, Dittmann J (2011) A context model for microphone forensics and its application in evaluations. Media Watermark Secur Forens III 7880:78800","journal-title":"Media Watermark Secur Forens III"},{"key":"2017_CR4","unstructured":"Xinxin LMYYLSN (2022) Semi-fragile audio watermarking algorithm in dwt domain. China Commun Engl Ed (4)"},{"issue":"2","key":"2017_CR5","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/TASLP.2014.2387385","volume":"23","author":"G Hua","year":"2015","unstructured":"Hua G, Goh J, Thing V (2015) Time-spread echo-based audio watermarking with optimized imperceptibility and robustness. IEEE-Acm Trans Audio Speech Lang Process 23(2):227\u2013239","journal-title":"IEEE-Acm Trans Audio Speech Lang Process"},{"key":"2017_CR6","unstructured":"Ji-Nian X, Yun-Zhe J, Er-Dong FU, Zheng H, Yan LI, Shao-Pei S (2014) Audio authenticity: duplicated audio segment detection in waveform audio file. J Shanghai Jiaotong Univ (Sci) (004), 019"},{"issue":"2","key":"2017_CR7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.4018\/IJDCF.2019040104","volume":"11","author":"X Huang","year":"2019","unstructured":"Huang X, Liu Z, Lu W, Liu H, Xiang S (2019) Fast and effective copy-move detection of digital audio based on auto segment. Int J Digit Crime Forens 11(2):47\u201362","journal-title":"Int J Digit Crime Forens"},{"key":"2017_CR8","doi-asserted-by":"publisher","first-page":"12843","DOI":"10.1109\/ACCESS.2017.2717842","volume":"5","author":"M Imran","year":"2017","unstructured":"Imran M, Ali Z, Bakhsh ST, Akram S (2017) Blind detection of copy-move forgery in digital audio forensics. IEEE Access 5:12843\u201312855","journal-title":"IEEE Access"},{"key":"2017_CR9","doi-asserted-by":"crossref","unstructured":"K\u00fc\u00e7\u00fcku\u01e7urlu B, Ustubioglu B, Ulutas G (2020) Duplicated audio segment detection with local binary pattern. In: 2020 43rd International conference on telecommunications and signal processing (TSP), pp 350\u2013353","DOI":"10.1109\/TSP49548.2020.9163568"},{"issue":"9","key":"2017_CR10","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1109\/TIFS.2019.2895965","volume":"14","author":"Q Yan","year":"2019","unstructured":"Yan Q, Yang R, Huang J (2019) Robust copy-move detection of speech recording using similarities of pitch and formant. IEEE Trans Inf Forens Secur 14(9):2331\u20132341","journal-title":"IEEE Trans Inf Forens Secur"},{"key":"2017_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118963","volume":"213","author":"U Beste","year":"2023","unstructured":"Beste U, Gul T, Guzin U (2023) Detection of audio copy-move-forgery with novel feature matching on mel spectrogram. Expert Syst Appl 213:118963","journal-title":"Expert Syst Appl"},{"key":"2017_CR12","doi-asserted-by":"crossref","unstructured":"Ustubioglu B, Tahaoglu G, Uluta G, Ustubioglu A, Kili M (2023) Audio forgery detection and localization with super-resolution spectrogram and keypoint-based clustering approach. J Supercomput","DOI":"10.21203\/rs.3.rs-2534047\/v1"},{"key":"2017_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2023.103507","volume":"75","author":"Z Su","year":"2023","unstructured":"Su Z, Li M, Zhang G, Wu Q, Wang Y (2023) Robust audio copy-move forgery detection on short forged slices using sliding window. J Inf Secur Appl 75:103507. https:\/\/doi.org\/10.1016\/j.jisa.2023.103507","journal-title":"J Inf Secur Appl"},{"key":"2017_CR14","first-page":"37","volume":"43","author":"Z Xie","year":"2018","unstructured":"Xie Z, Lu W, Liu X, Xue Y, Yeung Y (2018) Copy-move detection of digital audio based on multi-feature decision. J Inf Secur Appl 43:37\u201346","journal-title":"J Inf Secur Appl"},{"key":"2017_CR15","first-page":"4016","volume":"20","author":"Z Su","year":"2023","unstructured":"Su Z, Li M, Zhang G, Wu Q, Li M, Zhang W, Yao X (2023) Robust audio copy-move forgery detection using constant q spectral sketches and ga-svm. TDSC 20:4016\u20134031","journal-title":"TDSC"},{"key":"2017_CR16","doi-asserted-by":"crossref","unstructured":"Akdeniz F, Becerikli Y (2024) Recurrent neural network and long short-term memory models for audio copy-move forgery detection: a comprehensive study. J Supercomput:1\u201331","DOI":"10.1007\/s11227-024-05960-x"},{"key":"2017_CR17","doi-asserted-by":"crossref","unstructured":"Dincer S, Ustubioglu B, Ulutas G, Tahaoglu G, Ustubioglu A (2023) Robust audio forgery detection method based on capsule network. In: 2023 International conference on electrical and information technology (IEIT). IEEE, pp 243\u2013247","DOI":"10.1109\/IEIT59852.2023.10335590"},{"key":"2017_CR18","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1007\/s11760-022-02436-4","volume":"17","author":"U Arda","year":"2023","unstructured":"Arda U, Beste U, Guzin U (2023) Mel spectrogram-based audio forgery detection using cnn. SIViP 17:2211\u20132219","journal-title":"SIViP"},{"key":"2017_CR19","doi-asserted-by":"publisher","unstructured":"Ulutas G, Tahaoglu G, Ustubioglu B (2023) Deepfake audio detection with vision transformer based method. In: 2023 46th International conference on telecommunications and signal processing (TSP), pp 244\u2013247. https:\/\/doi.org\/10.1109\/TSP59544.2023.10197715","DOI":"10.1109\/TSP59544.2023.10197715"},{"key":"2017_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2024.110429","volume":"231","author":"K Peng","year":"2025","unstructured":"Peng K, Shi C, Li X, Qi C, Qiu X, Niu X (2025) Robust audio copy-move detection and localisation based on smoothed pseudo wigner-ville distribution and adaptive processing. Appl Acoust 231:110429. https:\/\/doi.org\/10.1016\/j.apacoust.2024.110429","journal-title":"Appl Acoust"},{"key":"2017_CR21","doi-asserted-by":"publisher","unstructured":"Saxena N, Sharma KK (2017) Image fusion scheme using two dimensional discrete fractional fourier transform. In: 2017 Conference on information and communication technology (CICT), pp 1\u20136. https:\/\/doi.org\/10.1109\/INFOCOMTECH.2017.8340631","DOI":"10.1109\/INFOCOMTECH.2017.8340631"},{"key":"2017_CR22","doi-asserted-by":"crossref","unstructured":"Diao S, Wan Y, Huang S, Ma H (2024) Research on cancer prediction and identification based on multimodal medical image fusion. In: Proceedings of the 2024 3rd international symposium on robotics, artificial intelligence and information engineering, pp 120\u2013124","DOI":"10.1145\/3689299.3689321"},{"key":"2017_CR23","doi-asserted-by":"crossref","unstructured":"Zhou M, Huang J, Yan K, Hong D, Jia X, Chanussot J, Li C (2024) A general spatial-frequency learning framework for multimodal image fusion. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3368112"},{"issue":"12","key":"2017_CR24","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2022","unstructured":"Li Z, Liu F, Yang W, Peng S, Zhou J (2022) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst 33(12):6999\u20137019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"2017_CR25","doi-asserted-by":"publisher","first-page":"379","DOI":"10.3390\/app15010379","volume":"15","author":"Y Liu","year":"2025","unstructured":"Liu Y, Guo W, Lu X, Kong L, Yan Z (2025) Class activation map guided backpropagation for discriminative explanations. Appl Sci 15(1):379","journal-title":"Appl Sci"},{"key":"2017_CR26","doi-asserted-by":"crossref","unstructured":"Jung H, Oh Y (2021) Towards better explanations of class activation mapping. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1336\u20131344","DOI":"10.1109\/ICCV48922.2021.00137"},{"key":"2017_CR27","doi-asserted-by":"crossref","unstructured":"Chefer H, Gur S, Wolf L (2021) Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 782\u2013791","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"2017_CR28","doi-asserted-by":"crossref","unstructured":"Shi G, Liu B, Walls L (2022) Data augmentation to improve the performance of ensemble learning for system failure prediction with limited observations. In: 2022 13th International conference on reliability, maintainability, and safety (ICRMS), pp 296\u2013300","DOI":"10.1109\/ICRMS55680.2022.9944577"},{"issue":"3","key":"2017_CR29","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):279\u2013283","journal-title":"IEEE Signal Process Lett"},{"issue":"7","key":"2017_CR30","first-page":"37","volume":"15","author":"KM Rezaul","year":"2024","unstructured":"Rezaul KM, Jewel M, Islam MS, Siddiquee K, Barua N, Rahman M, Sulaiman R, Shaikh M, Hamim M, Tanmoy F et al (2024) Enhancing audio classification through mfcc feature extraction and data augmentation with cnn and rnn models. Int J Adv Comput Sci Appl 15(7):37\u201353","journal-title":"Int J Adv Comput Sci Appl"},{"issue":"1","key":"2017_CR31","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13636-024-00336-8","volume":"2024","author":"S Hizlisoy","year":"2024","unstructured":"Hizlisoy S, Arslan RS, \u00c7olako\u011flu E (2024) Singer identification model using data augmentation and enhanced feature conversion with hybrid feature vector and machine learning. EURASIP J Audio Speech Music Process 2024(1):14","journal-title":"EURASIP J Audio Speech Music Process"},{"issue":"12","key":"2017_CR32","doi-asserted-by":"publisher","first-page":"34499","DOI":"10.1007\/s11042-023-17094-y","volume":"83","author":"AA Alemu","year":"2024","unstructured":"Alemu AA, Melese MD, Salau AO (2024) Ethio-semitic language identification using convolutional neural networks with data augmentation. Multimedia Tools Appl 83(12):34499\u201334514","journal-title":"Multimedia Tools Appl"},{"key":"2017_CR33","unstructured":"Halad N Modern standard Arabic phonetics for speech synthesis. http:\/\/en.arabicspeechcorpus.com\/"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02017-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02017-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02017-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T06:20:12Z","timestamp":1757226012000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02017-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2017"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02017-1","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,7,12]]},"assertion":[{"value":"25 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors are satisfied that the data we use is publicly available to others and consent to the use of audio data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"382"}}