{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T10:36:47Z","timestamp":1776076607959,"version":"3.50.1"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832226","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"774-781","source":"Crossref","is-referenced-by-count":15,"title":["Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CTRSVDD) Challenge 2024"],"prefix":"10.1109","author":[{"given":"Anmol","family":"Guragain","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"}]},{"given":"Tianchi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"}]},{"given":"Zihan","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"}]},{"given":"Hardik B.","family":"Sailor","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"}]},{"given":"Qiongqiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref3","article-title":"Asvspoof 5 evaluation plan","author":"Delgado","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832142"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448184"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2242"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446271"},{"key":"ref11","article-title":"Svdd challenge 2024: A singing voice deepfake detection challenge evaluation plan","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2405.05244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-787"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446072"},{"key":"ref16","article-title":"Target speech diarization with multimodal prompts","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv:2406.07198"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref18","first-page":"12449","article-title":"wav2vec 2.0: A framework for selfsupervised learning of speech representations","volume-title":"Proc. NeurIPS, 2020","volume":"33","author":"Baevski"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448049"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-659"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2296"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003763"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref36","first-page":"50221","article-title":"Disentangling voice and content with selfsupervision for speaker recognition","volume-title":"Proc. NeurIPS","volume":"36","author":"Liu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3385277"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2170"},{"key":"ref40","article-title":"Jvs-music: Japanese multispeaker singing-voice corpus","author":"Tamaru","year":"2020","journal-title":"arXiv preprint arXiv:2001.07044"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"}],"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\/10832226.pdf?arnumber=10832226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:09:10Z","timestamp":1737101350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832226","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}