{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T18:05:07Z","timestamp":1769537107715,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832200","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:31:27Z","timestamp":1737034287000},"page":"652-659","source":"Crossref","is-referenced-by-count":0,"title":["Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits"],"prefix":"10.1109","author":[{"given":"Sung-Feng","family":"Huang","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng-Cheng","family":"Kuo","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuesong","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao-Han Huck","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Acedemia Sinica"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"why AI-generated audio is so hard to detect","author":"News","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1052"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-738"},{"key":"ref4","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023","journal-title":"arXiv preprint arXiv:2308.14970"},{"key":"ref5","article-title":"The defender\u2019s perspective on automatic speaker verification: An overview","author":"Wu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref8","article-title":"Cfad: A chinese dataset for fake audio detection","author":"Ma","year":"2022","journal-title":"arXiv preprint arXiv:2207.12308"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747605"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746162"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094774"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101597"},{"key":"ref13","first-page":"1399","article-title":"A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"Proc. ICML","author":"Bai"},{"key":"ref14","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","volume-title":"Proc. NeurIPS","author":"Le"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref20","article-title":"ADD 2023: the second audio deepfake detection challenge","volume-title":"IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis (DADA 2023)","author":"Yi"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref26","article-title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","volume-title":"Proc. of ICLR","author":"Siuzdak"},{"key":"ref27","volume-title":"Zephyr: Direct distillation of LM alignment","author":"Tunstall","year":"2023"},{"key":"ref28","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Soviet physics doklady."},{"key":"ref29","first-page":"113","article-title":"TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection","volume-title":"Proceedings of IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis","volume":"750","author":"Liu"},{"key":"ref30","first-page":"18","article-title":"Convolutional recurrent neural network and multitask learning for manipulation region location","volume-title":"Proceedings of IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis","volume":"750","author":"Li"},{"key":"ref31","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832200.pdf?arnumber=10832200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:40:50Z","timestamp":1769488850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832200","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}