{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:07:45Z","timestamp":1779293265688,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"AIT Laboratory, FPT University, Danang Campus, Vietnam, 2025"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Korean Government","award":["2022R1F1A1065516"],"award-info":[{"award-number":["2022R1F1A1065516"]}]},{"DOI":"10.13039\/501100002648","name":"Research Fund of The Catholic University of Korea in 2025","doi-asserted-by":"publisher","award":["M-2025-B0002-00053"],"award-info":[{"award-number":["M-2025-B0002-00053"]}],"id":[{"id":"10.13039\/501100002648","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3571728","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:16:15Z","timestamp":1747761375000},"page":"95739-95752","source":"Crossref","is-referenced-by-count":5,"title":["A Comparative Study of Deep Audio Models for Spectrogram- and Waveform-Based SingFake Detection"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1091-0809","authenticated-orcid":false,"given":"Minh","family":"Nguyen-Duc","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4680-1984","authenticated-orcid":false,"given":"Luong Vuong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9263-1574","authenticated-orcid":false,"given":"Huy","family":"Nguyen-Ho-Nhat","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2132-2290","authenticated-orcid":false,"given":"Tri-Hai","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8921-5443","authenticated-orcid":false,"given":"O-Joun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"DiVISe: Direct visual-input speech synthesis preserving speaker characteristics and intelligibility","author":"Liu","year":"2025","journal-title":"arXiv:2503.05223"},{"key":"ref2","article-title":"OpenOmni: Advancing open-source omnimodal large language models with progressive multimodal alignment and real-time self-aware emotional speech synthesis","author":"Luo","year":"2025","journal-title":"arXiv:2501.04561"},{"key":"ref3","article-title":"PodAgent: A comprehensive framework for podcast generation","author":"Xiao","year":"2025","journal-title":"arXiv:2503.00455"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR52153.2021.00067"},{"issue":"1","key":"ref5","doi-asserted-by":"crossref","first-page":"6","DOI":"10.3390\/jcp5010006","article-title":"Partial fake speech attacks in the real world using deepfake audio","volume":"5","author":"Alali","year":"2025","journal-title":"J. Cybersecurity Privacy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0285333"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832284"},{"key":"ref8","article-title":"Detecting music deepfakes is easy but actually hard","author":"Afchar","year":"2024","journal-title":"arXiv:2405.04181"},{"key":"ref9","article-title":"From audio deepfake detection to AI-generated music detection\u2014A pathway and overview","author":"Li","year":"2024","journal-title":"arXiv:2412.00571"},{"key":"ref10","article-title":"SingFake: Singing voice deepfake detection","author":"Zang","year":"2023","journal-title":"arXiv:2309.07525"},{"key":"ref11","article-title":"Are music foundation models better at singing voice deepfake detection? Far-better fuse them with speech foundation models","author":"Phukan","year":"2024","journal-title":"arXiv:2409.14131"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832226"},{"key":"ref13","article-title":"From real to cloned singer identification","author":"Desblancs","year":"2024","journal-title":"arXiv:2407.08647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref15","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref16","article-title":"UniSpeech-SAT: Universal speech representation learning with speaker aware pre-training","author":"Chen","year":"2021","journal-title":"arXiv:2110.05752"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41545-024-00358-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3364682"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1016\/j.ultras.2023.107167","article-title":"Diagnosis of diabetes mellitus using high frequency ultrasound and convolutional neural network","volume":"136","author":"Lee","year":"2024","journal-title":"Ultrasonics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-22075-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-10882-w"},{"issue":"5","key":"ref23","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.3390\/cancers12051212","article-title":"Classification of breast cancer cells using the integration of high-frequency single-beam acoustic tweezers and convolutional neural networks","volume":"12","author":"Lim","year":"2020","journal-title":"Cancers"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100757"},{"issue":"5","key":"ref25","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3390\/a15050155","article-title":"A review of modern audio deepfake detection methods: Challenges and future directions","volume":"15","author":"Almutairi","year":"2022","journal-title":"Algorithms"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154404"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3714458"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2021.3089437"},{"key":"ref33","article-title":"ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech","author":"Wang","year":"2019","journal-title":"arXiv:1911.01601"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1254"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2025.3547861"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"issue":"1","key":"ref38","doi-asserted-by":"crossref","first-page":"114","DOI":"10.3390\/e24010114","article-title":"Singing voice detection: A survey","volume":"24","author":"Monir","year":"2022","journal-title":"Entropy"},{"key":"ref39","article-title":"Revisiting singing voice detection: A quantitative review and the future outlook","author":"Lee","year":"2018","journal-title":"arXiv:1806.01180"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2894-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888452"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-2242"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1185"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887871"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890293"},{"key":"ref46","article-title":"Understanding audio pattern using convolutional neural network from raw waveforms","author":"Qu","year":"2016","journal-title":"arXiv:1611.09524"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2341"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3287093"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref50","volume-title":"Ast Fine-Tuned on Audioset","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref52","volume-title":"Whisper Medium Fine-Tuned on Fleurs for Language Identification","author":"Gandhi","year":"2025"},{"key":"ref53","article-title":"FLEURS: Few-shot learning evaluation of universal representations of speech","author":"Conneau","year":"2022","journal-title":"arXiv:2205.12446"},{"key":"ref54","volume-title":"Hubert Base Model Pretrained on 960H of LibriSpeech","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref56","volume-title":"Unispeech-Sat Base Model Pretrained on 960H of LibriSpeech","year":"2025"},{"key":"ref57","article-title":"Hybrid spectrogram and waveform source separation","author":"D\u00e9fossez","year":"2021","journal-title":"arXiv:2111.03600"},{"key":"ref58","article-title":"Pyannote.Audio: Neural building blocks for speaker diarization","author":"Bredin","year":"2019","journal-title":"arXiv:1911.01255"},{"key":"ref59","first-page":"2229","article-title":"Evaluation: From precision, recall and F-measure to roc, informedness, markedness & correlation","volume":"2","author":"Powers","year":"2011","journal-title":"J. Mach. Learn. Technol."},{"key":"ref60","article-title":"Performance analysis and comparison of machine and deep learning algorithms for IoT data classification","author":"Vakili","year":"2020","journal-title":"arXiv:2001.09636"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIS50930.2021.9396043"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/11941439_114"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1214"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/chinsl.2004.1409642"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-202-5_5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11007653.pdf?arnumber=11007653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:43:18Z","timestamp":1749231798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3571728","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}