{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:41:59Z","timestamp":1774539719766,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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":["Int J Syst Assur Eng Manag"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s13198-024-02550-1","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T13:02:33Z","timestamp":1729256553000},"page":"5611-5636","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Publicly available datasets analysis and spectrogram-ResNet41 based improved features extraction for audio spoof attack detection"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5454-1561","authenticated-orcid":false,"given":"Nidhi","family":"Chakravarty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohit","family":"Dua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,18]]},"reference":[{"key":"2550_CR1","doi-asserted-by":"crossref","unstructured":"Adler A, and Schuckers ME (2005) Calculation of a composite DET curve. International Conference on Audio-and Video-Based Biometric Person Authentication, 860\u2013868","DOI":"10.1007\/11527923_90"},{"key":"2550_CR2","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1007\/s11235-011-9623-0","volume":"52","author":"RK Aggarwal","year":"2013","unstructured":"Aggarwal RK, Dave M (2013) Performance evaluation of sequentially combined heterogeneous feature streams for Hindi speech recognition system. Telecommun Syst 52:1457\u20131466. https:\/\/doi.org\/10.1007\/s11235-011-9623-0","journal-title":"Telecommun Syst"},{"key":"2550_CR3","unstructured":"Aravind PR, Nechiyil U, and Paramparambath N (2020) Audio spoofing verification using deep convolutional neural networks by transfer learning. ArXiv Preprint ArXiv:2008.03464"},{"key":"2550_CR4","first-page":"2033","volume":"2023","author":"Z Ba","year":"2023","unstructured":"Ba Z, Wen Q, Cheng P, Wang Y, Lin F, Lu L, Liu Z (2023) Transferring audio deepfake detection capability across languages. Proceed ACM Web Conf 2023:2033\u20132044","journal-title":"Proceed ACM Web Conf"},{"key":"2550_CR5","doi-asserted-by":"publisher","first-page":"101132","DOI":"10.1016\/j.csl.2020.101132","volume":"65","author":"R Baumann","year":"2021","unstructured":"Baumann R, Malik KM, Javed A, Ball A, Kujawa B, Malik H (2021) Voice spoofing detection corpus for single and multi-order audio replays. Comput Speech Lang 65:101132","journal-title":"Comput Speech Lang"},{"issue":"1","key":"2550_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"2550_CR7","doi-asserted-by":"crossref","unstructured":"Chakravarty N, and Dua M (2024a) A lightweight feature extraction technique for deepfake audio detection. Multimedia Tools and Applications, 1\u201325","DOI":"10.1007\/s11042-024-18217-9"},{"key":"2550_CR8","doi-asserted-by":"crossref","unstructured":"Chakravarty N, and Dua M (2024b) An improved feature extraction for Hindi language audio impersonation attack detection. Multimedia Tools and Applications, 1\u201326","DOI":"10.1007\/s11042-023-18104-9"},{"issue":"2","key":"2550_CR9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s42979-022-01557-4","volume":"4","author":"N Chakravarty","year":"2022","unstructured":"Chakravarty N, Dua M (2022) Noise robust ASV spoof detection using integrated features and time delay neural network. SN Comput Sci 4(2):127","journal-title":"SN Comput Sci"},{"issue":"1","key":"2550_CR10","first-page":"1","volume":"13","author":"N Chakravarty","year":"2023","unstructured":"Chakravarty N, Dua M (2023) Spoof detection using sequentially integrated image and audio features. Int J Comput Digit Syst 13(1):1","journal-title":"Int J Comput Digit Syst"},{"issue":"9","key":"2550_CR11","doi-asserted-by":"publisher","first-page":"096001","DOI":"10.1088\/1402-4896\/acea05","volume":"98","author":"N Chakravarty","year":"2023","unstructured":"Chakravarty N, Dua M (2023) Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks. Phys Scr 98(9):096001. https:\/\/doi.org\/10.1088\/1402-4896\/acea05","journal-title":"Phys Scr"},{"issue":"1","key":"2550_CR12","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10772-024-10093-w","volume":"27","author":"N Chakravarty","year":"2024","unstructured":"Chakravarty N, Dua M (2024c) Feature extraction using GTCC spectrogram and ResNet50 based classification for audio spoof detection. Int J Speech Technol 27(1):225\u2013237","journal-title":"Int J Speech Technol"},{"key":"2550_CR13","first-page":"285","volume":"2004","author":"J-M Cheng","year":"2004","unstructured":"Cheng J-M, Wang H-C (2004) A method of estimating the equal error rate for automatic speaker verification. Int Symposium Chin Spoken Language Process 2004:285\u2013288","journal-title":"Int Symposium Chin Spoken Language Process"},{"key":"2550_CR14","unstructured":"Delgado H, Evans N, Kinnunen T, Lee KA, Liu X, Nautsch A, Patino J, Sahidullah M, Todisco M, and Wang X (2021) ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan. ArXiv Preprint ArXiv:2109.00535"},{"key":"2550_CR15","doi-asserted-by":"crossref","unstructured":"Dhamyal H, Ali A, Qazi IA, and Raza AA (2021) Fake audio detection in resource-constrained settings using microfeatures. Interspeech, 4149\u20134153","DOI":"10.21437\/Interspeech.2021-524"},{"issue":"3","key":"2550_CR16","doi-asserted-by":"publisher","first-page":"6069","DOI":"10.1016\/j.eswa.2008.06.126","volume":"36","author":"P Dhanalakshmi","year":"2009","unstructured":"Dhanalakshmi P, Palanivel S, Ramalingam V (2009) Classification of audio signals using SVM and RBFNN. Expert Syst Appl 36(3):6069\u20136075","journal-title":"Expert Syst Appl"},{"issue":"4","key":"2550_CR17","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.1007\/s12652-021-02960-0","volume":"13","author":"M Dua","year":"2022","unstructured":"Dua M, Jain C, Kumar S (2022) LSTM and CNN based ensemble approach for spoof detection task in automatic speaker verification systems. J Ambient Intell Human Comput 13(4):1985\u20132000","journal-title":"J Ambient Intell Human Comput"},{"key":"2550_CR18","doi-asserted-by":"crossref","unstructured":"Dua M, Meena S, and Chakravarty N (2023) Audio deepfake detection using data augmented graph frequency cepstral coefficients. In: 2023 International Conference on System, Computation, Automation and Networking (ICSCAN), 1\u20136","DOI":"10.1109\/ICSCAN58655.2023.10395679"},{"key":"2550_CR19","doi-asserted-by":"crossref","unstructured":"Fu Z, Lu G, Ting KM, and Zhang D (2010). Learning naive Bayes classifiers for music classification and retrieval. In: 2010 20th International Conference on Pattern Recognition, 4589\u20134592","DOI":"10.1109\/ICPR.2010.1121"},{"key":"2550_CR20","first-page":"1068","volume":"2019","author":"A Gomez-Alanis","year":"2019","unstructured":"Gomez-Alanis A, Peinado AM, Gonzalez JA, Gomez AM (2019) A light convolutional GRU-RNN deep feature extractor for ASV spoofing detection. Proc Interspeech 2019:1068\u20131072","journal-title":"Proc Interspeech"},{"key":"2550_CR21","first-page":"1","volume":"1","author":"J Holdsworth","year":"1988","unstructured":"Holdsworth J, Nimmo-Smith I, Patterson R, Rice P (1988) Implementing a gammatone filter bank. Annex C of the SVOS Final Report: Part a: the Auditory Filterbank 1:1\u20135","journal-title":"Annex C of the SVOS Final Report: Part a: the Auditory Filterbank"},{"key":"2550_CR22","doi-asserted-by":"publisher","unstructured":"Hossan MA, Memon S, and Gregory MA (2010) A novel approach for MFCC feature extraction. In: 2010 4th International Conference on Signal Processing and Communication Systems, 1\u20135. https:\/\/doi.org\/10.1109\/ICSPCS.2010.5709752","DOI":"10.1109\/ICSPCS.2010.5709752"},{"key":"2550_CR23","unstructured":"Huang X, Acero A, Hon HW, and Reddy R (2001) Spoken language processing: A guide to theory, algorithm, and system development. Prentice hall PTR"},{"key":"2550_CR24","doi-asserted-by":"crossref","unstructured":"Joshi S, and Dua M (2022) LSTM-GTCC based approach for audio spoof detection. In: 2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON), 1:656\u2013661","DOI":"10.1109\/COM-IT-CON54601.2022.9850820"},{"key":"2550_CR25","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/978-981-19-8825-7_63","volume":"2022","author":"S Joshi","year":"2023","unstructured":"Joshi S, Dua M (2023) Multi-order replay attack detection using enhanced feature extraction and deep learning classification. Proceed Int Conf Recent Trends Comput: ICRTC 2022:739\u2013745","journal-title":"Proceed Int Conf Recent Trends Comput: ICRTC"},{"key":"2550_CR27","doi-asserted-by":"crossref","unstructured":"Liu X, Wang X, Sahidullah M, Patino J, Delgado H, Kinnunen T, Todisco M, Yamagishi J, Evans N, and Nautsch, A (2022) ASVspoof 2021: Towards spoofed and deepfake speech detection in the wild. ArXiv Preprint ArXiv:2210.02437","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"2550_CR28","doi-asserted-by":"crossref","unstructured":"Ma Y, Ren Z, and Xu S (2021) RW-Resnet: A novel speech anti-spoofing model using raw waveform. ArXiv Preprint ArXiv Preprint ArXiv:2108.05684","DOI":"10.21437\/Interspeech.2021-438"},{"key":"2550_CR29","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1109\/MIPR.2019.00106","volume":"2019","author":"KM Malik","year":"2019","unstructured":"Malik KM, Malik H, Baumann R (2019) Towards vulnerability analysis of voice-driven interfaces and countermeasures for replay attacks. IEEE Conf Multimed Inf Process Retrieval (MIPR) 2019:523\u2013528","journal-title":"IEEE Conf Multimed Inf Process Retrieval (MIPR)"},{"issue":"5","key":"2550_CR30","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/JSTSP.2020.2999828","volume":"14","author":"KM Malik","year":"2020","unstructured":"Malik KM, Javed A, Malik H, Irtaza A (2020) A Light-Weight Replay Detection Framework For Voice Controlled IoT Devices. IEEE J Select Topics Signal Process 14(5):982\u2013996. https:\/\/doi.org\/10.1109\/JSTSP.2020.2999828","journal-title":"IEEE J Select Topics Signal Process"},{"key":"2550_CR31","doi-asserted-by":"crossref","unstructured":"Mart\u00edn-Do\u00f1as JM, and \u00c1lvarez A (2022) The Vicomtech Audio Deepfake Detection System Based on Wav2vec2 for the 2022 ADD Challenge. ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 9241\u20139245","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"2550_CR32","unstructured":"Mathew JJ, Ahsan R, Furukawa S, Kumar JGK, Pallan H, Padda AS, Adamski S, Reddiboina M, and Pankajakshan A (2024) Towards the development of a real-time deepfake audio detection system in communication platforms. ArXiv Preprint ArXiv:2403.11778"},{"key":"2550_CR33","doi-asserted-by":"crossref","unstructured":"Meriem F, Messaoud B, and Bahia Y (2023) Texture analysis of edge mapped audio spectrogram for spoofing attack detection. Multimedia Tools and Applications, 1\u201323","DOI":"10.1007\/s11042-023-15329-6"},{"key":"2550_CR34","doi-asserted-by":"crossref","unstructured":"Mittal A, and Dua M (2021b) Constant Q cepstral coefficients and long short-term memory model-based automatic speaker verification system. Proceedings of International Conference on Intelligent Computing, Information and Control Systems, 895\u2013904","DOI":"10.1007\/978-981-15-8443-5_76"},{"issue":"2","key":"2550_CR35","first-page":"143","volume":"6","author":"A Mittal","year":"2021","unstructured":"Mittal A, Dua M (2021a) Automatic speaker verification system using three dimensional static and contextual variation-based features with two dimensional convolutional neural network. Int J Swarm Intell 6(2):143\u2013153","journal-title":"Int J Swarm Intell"},{"key":"2550_CR36","doi-asserted-by":"crossref","unstructured":"Murugappan M (2011) Human emotion classification using wavelet transform and KNN. 2011 International Conference on Pattern Analysis and Intelligence Robotics, 1:148\u2013153","DOI":"10.1109\/ICPAIR.2011.5976886"},{"issue":"1","key":"2550_CR37","first-page":"39","volume":"7","author":"JD Novakovi\u0107","year":"2017","unstructured":"Novakovi\u0107 JD, Veljovi\u0107 A, Ili\u0107 SS, Papi\u0107 \u017d, Milica T (2017) Evaluation of classification models in machine learning. Theory Appl Math Comput Sci 7(1):39\u201346","journal-title":"Theory Appl Math Comput Sci"},{"key":"2550_CR38","first-page":"1","volume":"2015","author":"D Paul","year":"2015","unstructured":"Paul D, Pal M, Saha G (2015) Novel speech features for improved detection of spoofing attacks. Annu IEEE India Conf (INDICON) 2015:1\u20136","journal-title":"Annu IEEE India Conf (INDICON)"},{"issue":"22","key":"2550_CR39","doi-asserted-by":"publisher","first-page":"31443","DOI":"10.1007\/s11042-022-12606-8","volume":"81","author":"R Rahmeni","year":"2022","unstructured":"Rahmeni R, Aicha AB, Ayed YB (2022) Voice spoofing detection based on acoustic and glottal flow features using conventional machine learning techniques. Multimed Tools Appl 81(22):31443\u201331467","journal-title":"Multimed Tools Appl"},{"key":"2550_CR40","doi-asserted-by":"crossref","unstructured":"Singh R, Biswas M, and Pal M (2022) Cloud detection using sentinel 2 imageries: a comparison of XGBoost, RF, SVM, and CNN algorithms. Geocarto International, 1\u201332","DOI":"10.1080\/10106049.2022.2146211"},{"key":"2550_CR41","unstructured":"Slaney M (1993) An efficient implementation of the Patterson-Holdsworth auditory filter bank. Apple Computer, Perception Group, Tech Rep. 35(8)"},{"key":"2550_CR42","first-page":"283","volume":"2016","author":"M Todisco","year":"2016","unstructured":"Todisco M, Delgado H, Evans NWD (2016) A new feature for automatic speaker verification anti-spoofing: constant q cepstral coefficients. Odyssey 2016:283\u2013290","journal-title":"Odyssey"},{"key":"2550_CR43","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1109\/TMM.2012.2199972","volume":"14","author":"X Valero","year":"2012","unstructured":"Valero X, Al\u00edas F (2012) Gammatone cepstral coefficients: biologically inspired features for non-speech audio classification. Multimed, IEEE Trans 14:1684\u20131689. https:\/\/doi.org\/10.1109\/TMM.2012.2199972","journal-title":"Multimed, IEEE Trans"},{"key":"2550_CR45","doi-asserted-by":"crossref","unstructured":"Voice conversion spoofing detection by exploring artifacts estimates, 80 Multimedia Tools and Applications 23561 (2021)","DOI":"10.1007\/s11042-020-10212-0"},{"key":"2550_CR46","doi-asserted-by":"crossref","unstructured":"Volkova M, Andzhukaev T, Lavrentyeva G, Novoselov S, and& Kozlov A (2019) Light CNN architecture enhancement for different types spoofing attack detection. Speech and Computer: 21st International Conference, SPECOM 2019, Istanbul, Turkey, Proceedings 21:520\u2013529","DOI":"10.1007\/978-3-030-26061-3_53"},{"key":"2550_CR47","unstructured":"Wang X, Vestman V, Sahidullah M, Delgado H, Nautsch A, Yamagishi J, Evans N, Kinnunen T, and Lee KA (2019) ASVspoof 2019: Future horizons in spoofed and fake audio detection. ArXiv Preprint ArXiv Preprint ArXiv:1904.05441"},{"key":"2550_CR48","unstructured":"Yamagishi J, Todisco M, Sahidullah M, Delgado H, Wang X, Evans N, Kinnunen T, Lee KA, Vestman V, and Nautsch A (2019) Asvspoof 2019: The 3rd automatic speaker verification spoofing and countermeasures challenge database"},{"key":"2550_CR49","doi-asserted-by":"crossref","unstructured":"Yuslee NS and Abdullah NAS (2021) Fake News Detection using Naive Bayes. 2021 IEEE 11th International Conference on System Engineering and Technology (ICSET), 112\u2013117","DOI":"10.1109\/ICSET53708.2021.9612540"}],"container-title":["International Journal of System Assurance Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-024-02550-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13198-024-02550-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-024-02550-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:04:18Z","timestamp":1732129458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13198-024-02550-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":47,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2550"],"URL":"https:\/\/doi.org\/10.1007\/s13198-024-02550-1","relation":{},"ISSN":["0975-6809","0976-4348"],"issn-type":[{"value":"0975-6809","type":"print"},{"value":"0976-4348","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,18]]},"assertion":[{"value":"17 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The data of this research do not involve any moral or ethical issues.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All the authors are informed and approve the submission of this manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}