{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T07:19:52Z","timestamp":1762759192556,"version":"build-2065373602"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":45,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"crossref","award":["IITP-2023-RS-2022-00164800","No.2021-0-00903, Development of Physical Channel Vulnerability-based Attacks and its Countermeasures for Reliable On-Device Deep Learning Accelerator Design"],"award-info":[{"award-number":["IITP-2023-RS-2022-00164800","No.2021-0-00903, Development of Physical Channel Vulnerability-based Attacks and its Countermeasures for Reliable On-Device Deep Learning Accelerator Design"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00500-025-10617-9","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T05:36:58Z","timestamp":1747373818000},"page":"4021-4032","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward almost-zero fault acceptance of deep learning-based voice authentication using small training dataset"],"prefix":"10.1007","volume":"29","author":[{"given":"Seung-A.","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun-Beom","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Woo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jejin","family":"Jo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Seob","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mee Lan","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5625-4067","authenticated-orcid":false,"given":"Dooho","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,16]]},"reference":[{"key":"10617_CR1","doi-asserted-by":"publisher","first-page":"16345","DOI":"10.1007\/s11042-018-7012-3","volume":"78","author":"A Abozaid","year":"2019","unstructured":"Abozaid A, Haggag A, Kasban H, Eltokhy M (2019) Multimodal biometric scheme for human authentication technique based on voice and face recognition fusion. Multimed Tools Appl 78:16345\u201316361","journal-title":"Multimed Tools Appl"},{"key":"10617_CR2","doi-asserted-by":"crossref","unstructured":"Ali MN, Schmalz VJ, Brutti A, Falavigna D (2021) A speech enhancement front-end for intent classification in noisy environments. In: 2021 29th European Signal Processing Conference (EUSIPCO), 471\u2013475. IEEE","DOI":"10.23919\/EUSIPCO54536.2021.9616322"},{"key":"10617_CR3","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neunet.2021.03.004","volume":"140","author":"Z Bai","year":"2021","unstructured":"Bai Z, Zhang X-L (2021) Speaker recognition based on deep learning: An overview. Neural Netw 140:65\u201399","journal-title":"Neural Netw"},{"key":"10617_CR4","first-page":"8","volume":"82","author":"H Chennamma","year":"2022","unstructured":"Chennamma H, Madhushree B (2022) A comprehensive survey on image authentication for tamper detection with localization. Multimed Tools Appl 82:8","journal-title":"Multimed Tools Appl"},{"key":"10617_CR5","doi-asserted-by":"crossref","unstructured":"Chung JS, Nagrani A, Zisserman A (2018) Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"10617_CR6","first-page":"69","volume":"76","author":"AX Glittas","year":"2021","unstructured":"Glittas AX, Gopalakrishnan L et al (2021) A low latency modular-level deeply integrated mfcc feature extraction architecture for speech recognition. Integration 76:69\u201375","journal-title":"Integration"},{"issue":"4","key":"10617_CR7","first-page":"3958","volume":"10","author":"SS Harakannanavar","year":"2019","unstructured":"Harakannanavar SS, Renukamurthy PC, Raja KB (2019) Comprehensive study of biometric authentication systems, challenges and future trends. Int J Adv Netw Appl 10(4):3958\u20133968","journal-title":"Int J Adv Netw Appl"},{"issue":"4","key":"10617_CR8","doi-asserted-by":"publisher","first-page":"2678","DOI":"10.1109\/TCE.2010.5681156","volume":"56","author":"D-J Kim","year":"2010","unstructured":"Kim D-J, Chung K-W, Hong K-S (2010) Person authentication using face, teeth and voice modalities for mobile device security. IEEE Trans Consum Electron 56(4):2678\u20132685","journal-title":"IEEE Trans Consum Electron"},{"key":"10617_CR9","doi-asserted-by":"crossref","unstructured":"Kumbhar HS, Bhandari SU (2019) Speech emotion recognition using mfcc features and lstm network. In: 2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), 1\u20133. IEEE","DOI":"10.1109\/ICCUBEA47591.2019.9129067"},{"key":"10617_CR10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2014.03.001","volume":"60","author":"A Larcher","year":"2014","unstructured":"Larcher A, Lee KA, Ma B, Li H (2014) Text-dependent speaker verification: classifiers, databases and rsr2015. Speech Commun 60:56\u201377","journal-title":"Speech Commun"},{"issue":"1","key":"10617_CR11","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1109\/TETCI.2023.3281843","volume":"8","author":"X Li","year":"2024","unstructured":"Li X, Guo M, Wang Z, Li J, Qin C (2024) Robust image hashing in encrypted domain. IEEE Trans Emerg Top Comput Intell 8(1):670\u2013683","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"10617_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani A, Chung JS, Xie W, Zisserman A (2020) Voxceleb: Large-scale speaker verification in the wild. Comput Speech Lang 60:101027","journal-title":"Comput Speech Lang"},{"key":"10617_CR13","doi-asserted-by":"crossref","unstructured":"Nagrani A, Chung JS, Zisserman A (2017) Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612","DOI":"10.21437\/Interspeech.2017-950"},{"key":"10617_CR14","doi-asserted-by":"crossref","unstructured":"Panayotov V, Chen G, Povey D, Khudanpur S (2015) Librispeech: An asr corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5206\u20135210 . IEEE","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"10617_CR15","first-page":"403","volume":"103","author":"E Rajaby","year":"2022","unstructured":"Rajaby E, Sayedi SM (2022) A structured review of sparse fast Fourier transform algorithms. Digit Signal Process 103:403","journal-title":"Digit Signal Process"},{"key":"10617_CR16","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s11042-021-10886-0","volume":"80","author":"H Rhayma","year":"2021","unstructured":"Rhayma H, Makhloufi A, Hamam H, Hamida A (2021) Semi-fragile watermarking scheme based on perceptual hash function (phf) for image tampering detection. Multimed Tools Appl 80:8","journal-title":"Multimed Tools Appl"},{"key":"10617_CR17","first-page":"194","volume":"4","author":"WJ Sheng","year":"2022","unstructured":"Sheng WJ, Kasmin IF, Amin S, Zainal NK (2022) Addressing user perception and implementing hedera hashgraph and voice recognition into multi-factor authentication (mfa) system. Int J Data Sci Adv Anal 4:194\u2013201","journal-title":"Int J Data Sci Adv Anal"},{"key":"10617_CR18","first-page":"999","volume":"2017","author":"D Snyder","year":"2017","unstructured":"Snyder D, Garcia-Romero D, Povey D, Khudanpur S (2017) Deep neural network embeddings for text-independent speaker verification. Interspeech 2017:999\u20131003","journal-title":"Interspeech"},{"key":"10617_CR19","doi-asserted-by":"crossref","unstructured":"Snyder D, Garcia-Romero D, Sell G, Povey D, Khudanpur S (2018) X-vectors: Robust dnn embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5329\u20135333. IEEE","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"10617_CR20","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.eswa.2017.08.015","volume":"90","author":"SS Tirumala","year":"2017","unstructured":"Tirumala SS, Shahamiri SR, Garhwal AS, Wang R (2017) Speaker identification features extraction methods: a systematic review. Expert Syst Appl 90:250\u2013271","journal-title":"Expert Syst Appl"},{"key":"10617_CR21","unstructured":"Victorian Information\u00a0Commissioner, O.O.: Biometrics and privacy\u2013issues and challenges. Available: 2023-05-11"},{"key":"10617_CR22","doi-asserted-by":"crossref","unstructured":"Wang L, Geng X (2009) Behavioral biometrics for human identification: Intelligent applications: Intelligent applications. IGI Global","DOI":"10.4018\/978-1-60566-725-6"},{"key":"10617_CR23","doi-asserted-by":"crossref","unstructured":"Wang Q, Lin X, Zhou M, Chen Y, Wang C, Li Q, Luo X (2019) Voicepop: A pop noise based anti-spoofing system for voice authentication on smartphones. In: IEEE INFOCOM 2019-IEEE Conference on Computer Communications, 2062\u20132070. IEEE","DOI":"10.1109\/INFOCOM.2019.8737422"},{"key":"10617_CR24","doi-asserted-by":"crossref","unstructured":"Wan L, Wang Q, Papir A, Moreno IL (2018) Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4879\u20134883. IEEE","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"10617_CR25","doi-asserted-by":"crossref","unstructured":"Wells A, Usman AB (2023) Security and performance of knowledge-based user authentication for smart devices. In: Information Security and Privacy in Smart Devices: Tools, Methods, and Applications, 41\u201370. IGI Global, Pennsylvania (USA). Chap. 2","DOI":"10.4018\/978-1-6684-5991-1.ch002"},{"issue":"1","key":"10617_CR26","doi-asserted-by":"publisher","first-page":"16","DOI":"10.30564\/ssid.v3i1.3152","volume":"3","author":"J Williamson","year":"2021","unstructured":"Williamson J, Curran K (2021) The role of multi-factor authentication for modern day security. Semicond Sci Inform Dev 3(1):16\u201323","journal-title":"Semicond Sci Inform Dev"},{"issue":"9","key":"10617_CR27","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/TASLP.2018.2831456","volume":"26","author":"C Zhang","year":"2018","unstructured":"Zhang C, Koishida K, Hansen JH (2018) Text-independent speaker verification based on triplet convolutional neural network embeddings. IEEE\/ACM Trans Audio Speech Lang Process 26(9):1633\u20131644","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10617_CR28","doi-asserted-by":"crossref","unstructured":"Zhang Y, Jiang F, Duan Z (2021) One-class learning towards synthetic voice spoofing detection. IEEE Signal Process Lett 28:937\u2013941","DOI":"10.1109\/LSP.2021.3076358"},{"key":"10617_CR29","doi-asserted-by":"crossref","unstructured":"Zhu Q-S, Zhang J, Zhang Z-Q, Dai L-R (2023) A joint speech enhancement and self-supervised representation learning framework for noise-robust speech recognition. Speech, and Language Processing, IEEE\/ACM Transactions on Audio","DOI":"10.1109\/TASLP.2023.3275033"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10617-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-025-10617-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10617-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T07:15:05Z","timestamp":1762758905000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-025-10617-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10617"],"URL":"https:\/\/doi.org\/10.1007\/s00500-025-10617-9","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"type":"print","value":"1432-7643"},{"type":"electronic","value":"1433-7479"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"26 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The funding information has been revised in the original version.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}