{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:15:23Z","timestamp":1781021723193,"version":"3.54.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T00:00:00Z","timestamp":1671408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T00:00:00Z","timestamp":1671408000000},"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":["SIViP"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s11760-022-02436-4","type":"journal-article","created":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T16:11:41Z","timestamp":1671466301000},"page":"2211-2219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["Mel spectrogram-based audio forgery detection using CNN"],"prefix":"10.1007","volume":"17","author":[{"given":"Arda","family":"Ustubioglu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beste","family":"Ustubioglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guzin","family":"Ulutas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,19]]},"reference":[{"key":"2436_CR1","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, Z., Lu, W., Liu, H., Xiang, S.: Fast and effective copy-move detection of digital audio based on auto segment. In: Digital Forensics and Forensic Investigations: Breakthroughs in Research and Practice, pp. 127\u2013142 (2020)","DOI":"10.4018\/978-1-7998-3025-2.ch011"},{"key":"2436_CR2","doi-asserted-by":"crossref","unstructured":"Wang, F., Li, C., Tian, L.: An algorithm of detecting audio copy-move forgery based on DCT and SVD. In: 2017 IEEE 17th International Conference on Communication Technology (ICCT), pp. 1652\u20131657 (2017).","DOI":"10.1109\/ICCT.2017.8359911"},{"key":"2436_CR3","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, S.T., Akram, S.: Blind detection of copy-move forgery in digital audio forensics. IEEE Access 5, 12843\u201312855 (2017)","journal-title":"IEEE Access"},{"key":"2436_CR4","doi-asserted-by":"crossref","unstructured":"Yan, Q., Yang, R., Huang, J.: Copy-move detection of audio recording with pitch similarity. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1782\u20131786 (2015)","DOI":"10.1109\/ICASSP.2015.7178277"},{"issue":"9","key":"2436_CR5","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.: Robust copy\u2014move detection of speech recording using similarities of pitch and formant. IEEE Trans. Inf. Forensics Secur. 14(9), 2331\u20132341 (2019)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"2436_CR6","doi-asserted-by":"crossref","unstructured":"Pan, X., Zhang, X., Lyu, S.: Detecting splicing in digital audios using local noise level estimation. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1841\u20131844 (2012)","DOI":"10.1109\/ICASSP.2012.6288260"},{"issue":"4","key":"2436_CR7","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1007\/s11042-014-2406-3","volume":"75","author":"J Chen","year":"2016","unstructured":"Chen, J., Xiang, S., Huang, H., Liu, W.: Detecting and locating digital audio forgeries based on singularity analysis with wavelet packet. Multimed. Tools Appl. 75(4), 2303\u20132325 (2016)","journal-title":"Multimed. Tools Appl."},{"key":"2436_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, V., Boulianne, G., Cardinal, P.: Content-based audio copy detection using nearest-neighbor mapping. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 261\u2013264 (2010)","DOI":"10.1109\/ICASSP.2010.5495963"},{"key":"2436_CR9","doi-asserted-by":"crossref","unstructured":"Muhammad, G., Alotaibi, Y.A., Alsulaiman, M., Huda, M.N.: Environment recognition using selected MPEG-7 audio features and mel-frequency cepstral coefficients. In: 2010 Fifth International Conference on Digital Telecommunications, pp. 11\u201316 (2010)","DOI":"10.1109\/ICDT.2010.10"},{"issue":"12","key":"2436_CR10","doi-asserted-by":"publisher","first-page":"13897","DOI":"10.1007\/s11042-016-3758-7","volume":"76","author":"H Zhao","year":"2017","unstructured":"Zhao, H., Chen, Y., Wang, R., Malik, H.: Audio splicing detection and localization using environmental signature. Multimed. Tools Appl. 76(12), 13897\u201313927 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"2436_CR11","doi-asserted-by":"crossref","unstructured":"Cuccovillo, L., Mann, S., Tagliasacchi, M., Aichroth, P.: Audio tampering detection via microphone classification. In: 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP), pp. 177\u2013182 (2013)","DOI":"10.1109\/MMSP.2013.6659284"},{"key":"2436_CR12","doi-asserted-by":"crossref","unstructured":"Buchholz, R., Kraetzer, C., Dittmann, J.: Microphone classification using Fourier coefficients. In: International Workshop on Information Hiding, pp. 235\u2013246 (2009)","DOI":"10.1007\/978-3-642-04431-1_17"},{"issue":"2","key":"2436_CR13","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1109\/TIFS.2016.2622012","volume":"12","author":"D Luo","year":"2016","unstructured":"Luo, D., Yang, R., Li, B., Huang, J.: Detection of double compressed AMR audio using stacked autoencoder. IEEE Trans. Inf. Forensics Secur. 12(2), 432\u2013444 (2016)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"2436_CR14","doi-asserted-by":"crossref","unstructured":"Lin, X., Kang, X.: Supervised audio tampering detection using an autoregressive model. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2142\u20132146 (2017)","DOI":"10.1109\/ICASSP.2017.7952535"},{"issue":"1","key":"2436_CR15","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3390\/electronics9010023","volume":"9","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Dai, S., Song, W., Zhang, L., Li, D.: Exposing speech resampling manipulation by local texture analysis on spectrogram images. Electronics 9(1), 23 (2019)","journal-title":"Electronics"},{"key":"2436_CR16","doi-asserted-by":"crossref","unstructured":"Capoferri, D., Borrelli, C., Bestagini, P., Antonacci, F., Sarti, A., Tubaro, S.: Speech audio splicing detection and localization exploiting reverberation cues. In: 2020 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1\u20136 (2020)","DOI":"10.1109\/WIFS49906.2020.9360900"},{"key":"2436_CR17","doi-asserted-by":"crossref","unstructured":"Jadhav, S., Patole, R., & Rege, P.: Audio splicing detection using convolutional neural network. In: 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1\u20135 (2020)","DOI":"10.1109\/ICCCNT45670.2019.8944345"},{"issue":"4","key":"2436_CR18","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/s12204-014-1515-5","volume":"19","author":"JN Xiao","year":"2014","unstructured":"Xiao, J.N., Jia, Y.Z., Fu, E.D., Huang, Z., Li, Y., Shi, S.P.: Audio authenticity: duplicated audio segment detection in waveform audio file. J. Shanghai Jiaotong Univ. (Science) 19(4), 392\u2013397 (2014)","journal-title":"J. Shanghai Jiaotong Univ. (Science)"},{"key":"2436_CR19","first-page":"37","volume":"43","author":"Z Xie","year":"2018","unstructured":"Xie, Z., Lu, W., Liu, X., Xue, Y., Yeung, Y.: Copy-move detection of digital audio based on multi-feature decision. J. Inf. Secur. Appl. 43, 37\u201346 (2018)","journal-title":"J. Inf. Secur. Appl."},{"issue":"6","key":"2436_CR20","doi-asserted-by":"publisher","first-page":"4559","DOI":"10.1121\/1.2916590","volume":"123","author":"SA Zahorian","year":"2008","unstructured":"Zahorian, S.A., Hu, H.: A spectral\/temporal method for robust fundamental frequency tracking. J. Acoust. Soc. Am. 123(6), 4559\u20134571 (2008)","journal-title":"J. Acoust. Soc. Am."},{"key":"2436_CR21","doi-asserted-by":"crossref","unstructured":"Todisco, M., Delgado, H., Evans, N.W.: A new feature for automatic speaker verification anti-spoofing: constant Q cepstral coefficients. In: Odyssey, vol. 2016, pp. 283\u2013290 (2016)","DOI":"10.21437\/Odyssey.2016-41"},{"key":"2436_CR22","doi-asserted-by":"crossref","unstructured":"Alluri, K.R., Achanta, S., Kadiri, S.R., Gangashetty, S.V., Vuppala, A.K.: Detection of replay attacks using single frequency filtering cepstral coefficients. In: Interspeech, pp. 2596\u20132600 (2017)","DOI":"10.21437\/Interspeech.2017-256"},{"key":"2436_CR23","doi-asserted-by":"crossref","unstructured":"Das, R.K., Yang, J., Li, H.: Long range acoustic features for spoofed speech detection. In: Interspeech, pp 1058\u20131062 (2019)","DOI":"10.21437\/Interspeech.2019-1887"},{"key":"2436_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, M.G., Kumar, S.R., Saranya, M.S., Bharathi, B., Murthy, H.A.: Spoof detection using time-delay shallow neural network and feature switching. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 1011\u20131017 (2019)","DOI":"10.1109\/ASRU46091.2019.9003824"},{"key":"2436_CR25","doi-asserted-by":"crossref","unstructured":"Chettri, B., Stoller, D., Morfi, V., Ram\u00edrez, M.A.M., Benetos, E., Sturm, B.L.: Ensemble models for spoofing detection in automatic speaker verification (2019). arXiv preprint arXiv:1904.04589","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"2436_CR26","doi-asserted-by":"crossref","unstructured":"Chen, T., Kumar, A., Nagarsheth, P., Sivaraman, G., Khoury, E.: Generalization of audio deepfake detection. In: Odyssey, pp. 132\u2013137 (2020)","DOI":"10.21437\/Odyssey.2020-19"},{"key":"2436_CR27","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1109\/LSP.2021.3076358","volume":"28","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Jiang, F., Duan, Z.: One-class learning towards synthetic voice spoofing detection. IEEE Signal Process. Lett. 28, 937\u2013941 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"2436_CR28","unstructured":"http:\/\/en.arabicspeechcorpus.com\/"},{"key":"2436_CR29","doi-asserted-by":"crossref","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S.: DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI\/Recon technical report n, 93, 27403 (1993)","DOI":"10.6028\/NIST.IR.4930"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02436-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-022-02436-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02436-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T04:18:08Z","timestamp":1684383488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-022-02436-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,19]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["2436"],"URL":"https:\/\/doi.org\/10.1007\/s11760-022-02436-4","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,19]]},"assertion":[{"value":"5 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare the following financial interests\/personal relationships which may be considered as potential competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that this article is original, has not been published before, and is not currently being considered for publication elsewhere. The authors confirm that the manuscript has been read and approved by all named authors and that there are no other persons who satisfied the criteria for authorship but are not listed. The authors further confirm that the order of authors listed in the manuscript has been approved by all of them.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}]}}