{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:03:25Z","timestamp":1780535005541,"version":"3.54.1"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T00:00:00Z","timestamp":1706140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T00:00:00Z","timestamp":1706140800000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18217-9","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T09:02:06Z","timestamp":1706173326000},"page":"67443-67467","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["A lightweight feature extraction technique for deepfake audio detection"],"prefix":"10.1007","volume":"83","author":[{"given":"Nidhi","family":"Chakravarty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohit","family":"Dua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,25]]},"reference":[{"key":"18217_CR1","volume-title":"A study of instance-based algorithms for supervised learning tasks: Mathematical, empirical, and psychological evaluations","author":"DW Aha","year":"1990","unstructured":"Aha DW (1990) A study of instance-based algorithms for supervised learning tasks: Mathematical, empirical, and psychological evaluations. University of California, Irvine"},{"issue":"3","key":"18217_CR2","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1007\/s00530-023-01060-7","volume":"29","author":"A Antil","year":"2023","unstructured":"Antil A, Dhiman C (2023) A two stream face anti-spoofing framework using multi-level deep features and ELBP features. Multimed Syst 29(3):1361\u20131376. https:\/\/doi.org\/10.1007\/s00530-023-01060-7","journal-title":"Multimed Syst"},{"key":"18217_CR3","doi-asserted-by":"publisher","unstructured":"Ba Z, Wen Q, Cheng P, Wang Y, Lin F, Lu L, Liu Z (2023) Transferring audio deepfake detection capability across languages. In: Proceedings of the ACM Web Conference 2023 (pp 2033\u20132044). https:\/\/doi.org\/10.1145\/3543507.3583222","DOI":"10.1145\/3543507.3583222"},{"key":"18217_CR4","doi-asserted-by":"publisher","first-page":"115465","DOI":"10.1016\/j.eswa.2021.115465","volume":"184","author":"DM Ballesteros","year":"2021","unstructured":"Ballesteros DM, Rodriguez-Ortega Y, Renza D, Arce G (2021) Deep4SNet: deep learning for fake speech classification. Exp Syst Appl 184:115465. https:\/\/doi.org\/10.1016\/j.eswa.2021.115465","journal-title":"Exp Syst Appl"},{"key":"18217_CR5","doi-asserted-by":"publisher","unstructured":"Bhakre S, Bang A (2016) Emotion recognition on the basis of audio signal using Naive Bayes classifier.https:\/\/doi.org\/10.1109\/ICACCI.2016.7732408","DOI":"10.1109\/ICACCI.2016.7732408"},{"issue":"27","key":"18217_CR6","doi-asserted-by":"publisher","first-page":"39343","DOI":"10.1007\/s11042-022-12380-7","volume":"81","author":"KP Bharath","year":"2022","unstructured":"Bharath KP, Kumar MR (2022) Replay spoof detection for speaker verification system using magnitude-phase-instantaneous frequency and energy features. Multimed Tools Appl 81(27):39343\u201339366","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"18217_CR7","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":"18217_CR8","doi-asserted-by":"publisher","unstructured":"Chaiwongyen A, Songsriboonsit N, Duangpummet S, Karnjana J, Kongprawechnon W, Unoki M (2022) Contribution of timbre and shimmer features to deepfake speech detection. In: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, pp 97\u2013103). https:\/\/doi.org\/10.23919\/APSIPAASC55919.2022.9980281","DOI":"10.23919\/APSIPAASC55919.2022.9980281"},{"key":"18217_CR9","doi-asserted-by":"crossref","unstructured":"Chakravarty N, Dua M (2023) Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks. Physica Scripta 98(9):096001","DOI":"10.1088\/1402-4896\/acea05"},{"key":"18217_CR10","doi-asserted-by":"publisher","unstructured":"Chen T, Kumar A, Nagarsheth P, Sivaraman G, Khoury E (2020) Generalization of audio deepfake detection. In: Odyssey (pp 132\u2013137). https:\/\/doi.org\/10.21437\/Odyssey.2020-19","DOI":"10.21437\/Odyssey.2020-19"},{"key":"18217_CR11","doi-asserted-by":"publisher","unstructured":"Cheng JM, Wang HC (2004) A method of estimating the equal error rate for automatic speaker verification. In: 2004 International Symposium on Chinese Spoken Language Processing. IEEE, pp 285\u2013288. https:\/\/doi.org\/10.1109\/CHINSL.2004.1409642","DOI":"10.1109\/CHINSL.2004.1409642"},{"key":"18217_CR12","doi-asserted-by":"crossref","unstructured":"Chettri B, Stoller D, Morfi V, Ram\u00edrez MAM, Benetos E, Sturm BL (2019) Ensemble models for spoofing detection in automatic speaker verification. ArXiv Preprint Preprint ArXiv:1904.04589","DOI":"10.21437\/Interspeech.2019-2505"},{"issue":"5","key":"18217_CR13","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/JSTSP.2020.2999185","volume":"14","author":"A Chintha","year":"2020","unstructured":"Chintha A, Thai B, Sohrawardi SJ, Bhatt K, Hickerson A, Wright M, Ptucha R (2020) Recurrent convolutional structures for audio spoof and video deepfake detection. IEEE J Sel Top Signal Proc 14(5):1024\u20131037","journal-title":"IEEE J Sel Top Signal Proc"},{"key":"18217_CR14","doi-asserted-by":"publisher","unstructured":"Das RK (2021) Known-unknown data augmentation strategies for detection of logical access, physical access and speech deepfake attacks: ASVspoof 2021. Proc. 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge, pp 29\u201336. https:\/\/doi.org\/10.21437\/ASVSPOOF.2021-5","DOI":"10.21437\/ASVSPOOF.2021-5"},{"key":"18217_CR15","unstructured":"Dave N (2013) Feature extraction methods LPC, PLP and MFCC in speech recognition. Int J Adv Res Eng Technol 1(6):1\u20134"},{"key":"18217_CR16","doi-asserted-by":"crossref","unstructured":"Dewi SP, Prasasti AL, Irawan B (2019) The study of baby crying analysis using MFCC and LFCC in different classification methods. 2019 IEEE International Conference on Signals and Systems (ICSigSys), pp 18\u201323","DOI":"10.1109\/ICSIGSYS.2019.8811070"},{"key":"18217_CR17","doi-asserted-by":"crossref","unstructured":"Doan T-P, Nguyen-Vu L, Jung S, Hong K (2023) BTS-E: Audio deepfake detection using breathing-talking-silence encoder. ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10095927"},{"key":"18217_CR18","doi-asserted-by":"publisher","first-page":"103517","DOI":"10.1016\/j.bspc.2022.103517","volume":"74","author":"M Dua","year":"2022","unstructured":"Dua M, Sadhu A, Jindal A, Mehta R (2022) A hybrid noise robust model for multireplay attack detection in Automatic speaker verification systems. Biomed Signal Proc Control 74:103517. https:\/\/doi.org\/10.1016\/j.bspc.2022.103517","journal-title":"Biomed Signal Proc Control"},{"key":"18217_CR19","doi-asserted-by":"publisher","unstructured":"Fathan A, Alam J, Kang WH (2022) Mel-spectrogram image-based end-to-end audio deepfake detection under channel-mismatched conditions. In: 2022 IEEE International Conference on Multimedia and Expo (ICME). Taipei, Taiwan. IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859621","DOI":"10.1109\/ICME52920.2022.9859621"},{"key":"18217_CR20","doi-asserted-by":"publisher","unstructured":"Gharde D, Suryanarayan N, Srinivas KS (2022) Detection of morphed face, body, audio signals using deep neural networks. In: 2022 IEEE 7th International conference for Convergence in Technology (I2CT). IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/I2CT54291.2022.9825423","DOI":"10.1109\/I2CT54291.2022.9825423"},{"key":"18217_CR21","doi-asserted-by":"publisher","unstructured":"Godoy A, Simoes F, Stuchi JA, Angeloni MDA, Uliani M, Violato R (2015) Using deep learning for detecting spoofing attacks on speech signals. arXiv preprint arXiv:1508.01746. https:\/\/doi.org\/10.48550\/arXiv.1508.01746","DOI":"10.48550\/arXiv.1508.01746"},{"key":"18217_CR22","doi-asserted-by":"publisher","unstructured":"Grama L, Rusu C (2017) Audio signal classification using linear predictive coding and random forests. 2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp 1\u20139. https:\/\/doi.org\/10.1109\/SPED.2017.7990431","DOI":"10.1109\/SPED.2017.7990431"},{"key":"18217_CR23","doi-asserted-by":"publisher","unstructured":"Guo G, Wang H, Bell D, Bi Y, Greer K (2003) KNN model-based approach in classification. Lect Notes Comput Sci 2888:986\u2013996. https:\/\/doi.org\/10.1007\/978-3-540-39964-3_62","DOI":"10.1007\/978-3-540-39964-3_62"},{"key":"18217_CR24","doi-asserted-by":"publisher","unstructured":"Hanil\u00e7i C, Kinnunen T, Sahidullah M, Sizov A (2015) Classifiers for synthetic speech detection: A Comparison. https:\/\/doi.org\/10.21437\/Interspeech.2015-466","DOI":"10.21437\/Interspeech.2015-466"},{"key":"18217_CR25","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"18217_CR26","doi-asserted-by":"publisher","unstructured":"Hossan MA, Memon S, Gregory MA (2010) A novel approach for MFCC feature extraction. 2010 4th International Conference on Signal Processing and Communication Systems, pp 1\u20135. https:\/\/doi.org\/10.1109\/ICSPCS.2010.5709752","DOI":"10.1109\/ICSPCS.2010.5709752"},{"issue":"4","key":"18217_CR27","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F Jelinek","year":"1976","unstructured":"Jelinek F (1976) Continuous speech recognition by statistical methods. Proc IEEE 64(4):532\u2013556. https:\/\/doi.org\/10.1109\/PROC.1976.10159","journal-title":"Proc IEEE"},{"key":"18217_CR28","doi-asserted-by":"crossref","unstructured":"Kang WH, Alam J, Fathan A (2021) Investigation on activation functions for robust end-to-end spoofing attack detection system. Proc. 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge, pp 83\u201388","DOI":"10.21437\/ASVSPOOF.2021-13"},{"key":"18217_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/10984697_1","volume-title":"Support Vector Machines Theory and Applications","author":"V Kecman","year":"2005","unstructured":"Kecman V (2005) Support vector machines \u2013 an introduction BT. In: Wang L (ed) Support Vector Machines Theory and Applications. Springer Berlin Heidelberg, pp 1\u201347. https:\/\/doi.org\/10.1007\/10984697_1"},{"key":"18217_CR30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.5829\/idosi.wasj.2013.21.mae.99935","volume":"21","author":"O Khalifa","year":"2013","unstructured":"Khalifa O, El-Darymli K, Daoud J (2013) Statistical modeling for speech recognition. World Appl Sci J 21:115\u2013122. https:\/\/doi.org\/10.5829\/idosi.wasj.2013.21.mae.99935","journal-title":"World Appl Sci J"},{"key":"18217_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-06297-w","author":"J Khochare","year":"2021","unstructured":"Khochare J, Joshi C, Yenarkar B, Suratkar S, Kazi F (2021) A deep learning framework for audio deepfake detection. Arab J Sci Eng. https:\/\/doi.org\/10.1007\/s13369-021-06297-w","journal-title":"Arab J Sci Eng"},{"issue":"3","key":"18217_CR32","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.1007\/s13369-021-06297-w","volume":"47","author":"J Khochare","year":"2022","unstructured":"Khochare J, Joshi C, Yenarkar B, Suratkar S, Kazi F (2022) A deep learning framework for audio deepfake detection. Arab J Sci Eng 47(3):3447\u20133458","journal-title":"Arab J Sci Eng"},{"key":"18217_CR33","doi-asserted-by":"publisher","unstructured":"Kinnunen T, Sahidullah M, Delgado H, Todisco M, Evans N, Yamagishi J, Lee KA (2017) The ASVspoof 2017 challenge: assessing the limits of replay spoofing attack detection. Proc. Interspeech 2017:2\u20136. https:\/\/doi.org\/10.21437\/Interspeech.2017-1111","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"18217_CR34","doi-asserted-by":"publisher","unstructured":"Li Z, Tang H, Peng Z, Qi G-J, Tang J (2023) Knowledge-guided semantic transfer network for few-shot image recognition. IEEE Transactions on Neural Networks and Learning Systems, pp 1\u201315. https:\/\/doi.org\/10.1109\/TNNLS.2023.3240195","DOI":"10.1109\/TNNLS.2023.3240195"},{"issue":"6","key":"18217_CR35","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/s00530-002-0065-0","volume":"8","author":"L Lu","year":"2003","unstructured":"Lu L, Zhang H-J, Li SZ (2003) Content-based audio classification and segmentation by using support vector machines. Multimed Syst 8(6):482\u2013492","journal-title":"Multimed Syst"},{"key":"18217_CR36","doi-asserted-by":"crossref","unstructured":"Lv Z, Zhang S, Tang K, Hu P (2022) Fake audio detection based on unsupervised pretraining models. ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 9231\u20139235","DOI":"10.1109\/ICASSP43922.2022.9747605"},{"key":"18217_CR37","doi-asserted-by":"publisher","unstructured":"Meriem F, Messaoud B, Bahia Y (2023)\u00a0Texture analysis of edge mapped audio spectrogram for spoofing attack detection. Multimed Tools Appl 1\u201323. https:\/\/doi.org\/10.1007\/s11042-023-15329-6","DOI":"10.1007\/s11042-023-15329-6"},{"issue":"2","key":"18217_CR38","first-page":"143","volume":"6","author":"A Mittal","year":"2021","unstructured":"Mittal A, Dua M (2021) 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":"18217_CR39","doi-asserted-by":"crossref","unstructured":"Mittal A, Dua M (2022) Static\u2013dynamic features and hybrid deep learning models-based spoof detection system for ASV. Complex Int Syst 8(2):1153\u20131166","DOI":"10.1007\/s40747-021-00565-w"},{"key":"18217_CR40","doi-asserted-by":"publisher","unstructured":"Mittal A, Dua M (2021) Constant Q cepstral coefficients and long short-term memory model-based automatic speaker verification system. In: Proceedings of international conference on intelligent computing, information and control systems: ICICCS 2020. Springer Singapore, pp 895\u2013904. https:\/\/doi.org\/10.1007\/978-981-15-8443-5_76","DOI":"10.1007\/978-981-15-8443-5_76"},{"key":"18217_CR41","doi-asserted-by":"publisher","first-page":"8483","DOI":"10.1007\/s00521-019-04468-3","volume":"31","author":"H Mukherjee","year":"2019","unstructured":"Mukherjee H, Ghosh S, Sen S, SkMd O, Santosh KC, Phadikar S, Roy K (2019) Deep learning for spoken language identification: Can we visualize speech signal patterns? Neural Comput Appl 31:8483\u20138501","journal-title":"Neural Comput Appl"},{"key":"18217_CR42","doi-asserted-by":"publisher","unstructured":"Murugappan M (2011) Human emotion classification using wavelet transform and KNN. In: 2011 international conference on pattern analysis and intelligence robotics (vol 1). IEEE, pp 148\u2013153. https:\/\/doi.org\/10.1109\/ICPAIR.2011.5976886","DOI":"10.1109\/ICPAIR.2011.5976886"},{"key":"18217_CR43","doi-asserted-by":"crossref","unstructured":"Neelima M, Prabha IS (2023) Optimized deep network based spoof detection in automatic speaker verification system. Multimed Tools Appl 1\u201319","DOI":"10.1007\/s11042-023-16127-w"},{"issue":"1","key":"18217_CR44","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"},{"issue":"10","key":"18217_CR45","doi-asserted-by":"publisher","first-page":"1942","DOI":"10.1109\/TASLP.2017.2732162","volume":"25","author":"Y Qian","year":"2017","unstructured":"Qian Y, Chen N, Dinkel H, Wu Z (2017) Deep feature engineering for noise robust spoofing detection. IEEE\/ACM Trans Audio, Speech, Lang Proc 25(10):1942\u20131955","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Proc"},{"key":"18217_CR46","doi-asserted-by":"publisher","unstructured":"Reimao R, Tzerpos V (2019) FoR: A dataset for synthetic speech detection. https:\/\/doi.org\/10.1109\/SPED.2019.8906599","DOI":"10.1109\/SPED.2019.8906599"},{"key":"18217_CR47","unstructured":"Shan M, Tsai TJ (2020) A cross-verification approach for protecting world leaders from fake and tampered audio. ArXiv Preprint ArXiv:2010.12173"},{"issue":"1","key":"18217_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00492-0","volume":"8","author":"C Shorten","year":"2021","unstructured":"Shorten C, Khoshgoftaar TM, Furht B (2021) Text data augmentation for deep learning. J Big Data 8(1):1\u201334","journal-title":"J Big Data"},{"key":"18217_CR49","doi-asserted-by":"publisher","unstructured":"Singh R, Biswas M, Pal M (2022) Cloud detection using sentinel 2 imageries: a comparison of XGBoost, RF, SVM, and CNN algorithms. Geocarto Int 38(1):1\u201332. https:\/\/doi.org\/10.1080\/10106049.2022.2146211","DOI":"10.1080\/10106049.2022.2146211"},{"key":"18217_CR50","doi-asserted-by":"crossref","unstructured":"Tang H, Li Z, Peng Z, Tang J (2020) Blockmix: meta regularization and self-calibrated inference for metric-based meta-learning. Proceedings of the 28th ACM International Conference on Multimedia, pp 610\u2013618","DOI":"10.1145\/3394171.3413884"},{"key":"18217_CR51","doi-asserted-by":"crossref","unstructured":"Tang H, Liu J, Yan S, Yan R, Li Z, Tang J (2023) M3Net: Multi-view encoding, matching, and fusion for few-shot fine-grained action recognition. In Proceedings of the 31st ACM International Conference on Multimedia, pp 1719\u20131728","DOI":"10.1145\/3581783.3612221"},{"key":"18217_CR52","doi-asserted-by":"publisher","first-page":"108792","DOI":"10.1016\/j.patcog.2022.108792","volume":"130","author":"H Tang","year":"2022","unstructured":"Tang H, Yuan C, Li Z, Tang J (2022) Learning attention-guided pyramidal features for few-shot fine-grained recognition. Pattern Recogn 130:108792","journal-title":"Pattern Recogn"},{"issue":"2","key":"18217_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-020-0114-9","volume":"1","author":"D Theckedath","year":"2020","unstructured":"Theckedath D, Sedamkar RR (2020) Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks. SN Computer Science 1(2):1\u20137","journal-title":"SN Computer Science"},{"issue":"10","key":"18217_CR54","first-page":"2449","volume":"13","author":"R Thiruvengatanadhan","year":"2017","unstructured":"Thiruvengatanadhan R (2017) Speech\/Music Classification using MFCC and KNN. Int J Comput Intell Res 13(10):2449\u20132452","journal-title":"Int J Comput Intell Res"},{"key":"18217_CR55","unstructured":"Wang X, Vestman V, Sahidullah M, Delgado H, Nautsch A, Yamagishi J, Evans N, Kinnunen T, Lee KA (2019) ASVspoof 2019: Future horizons in spoofed and fake audio detection. ArXiv Preprint ArXiv:1904.05441"},{"key":"18217_CR56","first-page":"713","volume":"15","author":"GI Webb","year":"2010","unstructured":"Webb GI, Keogh E, Miikkulainen R (2010) Na\u00efve bayes. Encycl Mach Learn 15:713\u2013714","journal-title":"Encycl Mach Learn"},{"issue":"2","key":"18217_CR57","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s00530-015-0476-3","volume":"23","author":"F Wu","year":"2017","unstructured":"Wu F, Xu L, Kumari S, Li X (2017) An improved and anonymous two-factor authentication protocol for health-care applications with wireless medical sensor networks. Multimed Syst 23(2):195\u2013205. https:\/\/doi.org\/10.1007\/s00530-015-0476-3","journal-title":"Multimed Syst"},{"key":"18217_CR58","doi-asserted-by":"publisher","unstructured":"Wu Z, Kinnunen T, Evans N, Yamagishi J, Hanil\u00e7i C, Sahidullah M, Sizov A (2015) ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge. Proc. Interspeech 2015:2037\u20132041. https:\/\/doi.org\/10.21437\/Interspeech.2015-462","DOI":"10.21437\/Interspeech.2015-462"},{"key":"18217_CR59","doi-asserted-by":"publisher","unstructured":"Xue J, Fan C, Lv Z, Tao J, Yi J, Zheng C, ... Shao S (2022) Audio deepfake detection based on a combination of f0 information and real plus imaginary spectrogram features. In: Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia, pp 19\u201326. https:\/\/doi.org\/10.1145\/3552466.3556526","DOI":"10.1145\/3552466.3556526"},{"key":"18217_CR60","doi-asserted-by":"crossref","unstructured":"Yamagishi J, Wang X, Todisco M, Sahidullah M, Patino J, Nautsch A, Liu X, Lee K, Kinnunen TH, Evans NW, Delgado H (2021) ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. https:\/\/arxiv.org\/abs\/2109.00537","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"18217_CR61","doi-asserted-by":"publisher","unstructured":"Yang J, Das R, Li H (2018) Extended constant-Q cepstral coefficients for detection of spoofing attacks. https:\/\/doi.org\/10.23919\/APSIPA.2018.8659537","DOI":"10.23919\/APSIPA.2018.8659537"},{"key":"18217_CR62","doi-asserted-by":"publisher","unstructured":"Yi J, Fu R, Tao J, Nie S, Ma H, Wang C, Wang T, Tian Z, Bai Y, Fan C (2022) Add 2022: the first audio deep synthesis detection challenge. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 9216\u20139220. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746939","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"issue":"8","key":"18217_CR63","doi-asserted-by":"publisher","first-page":"3947","DOI":"10.1109\/TCSVT.2023.3236636","volume":"33","author":"Z Zha","year":"2023","unstructured":"Zha Z, Tang H, Sun Y, Tang J (2023) Boosting few-shot fine-grained recognition with background suppression and foreground alignment. IEEE Trans Circuits Syst Video Technol 33(8):3947\u20133961. https:\/\/doi.org\/10.1109\/TCSVT.2023.3236636","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"18217_CR64","doi-asserted-by":"publisher","unstructured":"Zhao Z, Gong Z, Niu M, Ma J, Wang H, Zhang Z, Li Y (2022) Automatic respiratory sound classification via multi-branch temporal convolutional network. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 9102\u20139106. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746182","DOI":"10.1109\/ICASSP43922.2022.9746182"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18217-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18217-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18217-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T01:08:46Z","timestamp":1721610526000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18217-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,25]]},"references-count":64,"journal-issue":{"issue":"26","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["18217"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18217-9","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,25]]},"assertion":[{"value":"23 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"I, Dr. Mohit Dua, on the behalf of all the authors declare that:","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study did not receive any finding from any resource.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}},{"value":"All the authors and the submitted manuscript do not have any conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}