{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:40Z","timestamp":1776886420449,"version":"3.51.2"},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/slt61566.2024.10832292","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1254-1261","source":"Crossref","is-referenced-by-count":4,"title":["The Database and Benchmark For the Source Speaker Tracing Challenge 2024"],"prefix":"10.1109","author":[{"given":"Ze","family":"Li","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Lin","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Yao","sequence":"additional","affiliation":[{"name":"OPPO,AI Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Suo","sequence":"additional","affiliation":[{"name":"OPPO,AI Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexin","family":"Cai","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiromitsu","family":"Nishizaki","sequence":"additional","affiliation":[{"name":"University of Yamanashi, 4-4-37, Takeda, Kofu,Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences,Yamanashi,Japan,400-8510"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref8","article-title":"Add 2023: the second audio deepfake detection challenge","author":"Yi","year":"2023","journal-title":"arXiv preprint arXiv:2305.13774"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638222"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096733"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref14","article-title":"Mediumvc: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv:2110.02500"},{"key":"ref15","article-title":"Styletts: A style-based generative model for natural and diverse text-to-speech synthesis","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv:2205.15439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746048"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref21","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. of ICLR","author":"Popov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref23","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"Proc. of ICML. PMLR","author":"Casanova"},{"key":"ref24","article-title":"Controlvc: Zero-shot voice conversion with time-varying controls on pitch and speed","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2209.11866"},{"key":"ref25","first-page":"2283","article-title":"Diffhiervc: Diffusion-based hierarchical voice conversion with robust pitch generation and masked prior for zero-shot speaker adaptation","author":"Choi","year":"2023","journal-title":"International Speech Communication Association"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2298"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447984"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5610-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref35","article-title":"Conditionally adaptive multi-task learning: Improving transfer learning in nlp using fewer parameters & less data","volume-title":"Proc. of ICLR","author":"Pilault"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref38","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref40","article-title":"Fixing weight decay regularization in adam","volume-title":"Proc. of ICLR","author":"Loshchilov"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-266"}],"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\/10832292.pdf?arnumber=10832292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:19Z","timestamp":1737398359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832292","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}