{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:43Z","timestamp":1776886423124,"version":"3.51.2"},"reference-count":43,"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\/slt61566.2024.10832140","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1247-1253","source":"Crossref","is-referenced-by-count":2,"title":["Speaker Contrastive Learning For Source Speaker Tracing"],"prefix":"10.1109","author":[{"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongmei","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI),China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI),China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjie","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI),China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI),China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI),China Telecom,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,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","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. ICLR","author":"Goodfellow"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref5","article-title":"Intriguing properties of neural networks","volume-title":"Proc. ICLR","author":"Szegedy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23362"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1352"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2012-465"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref16","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096733"},{"key":"ref18","article-title":"The database and benchmark for source speaker verification against voice conversion","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2406.04951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022498"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096642"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746048"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref30","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref32","first-page":"2709","article-title":"Yourtts: Towards zero-shot multispeaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2298"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447984"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref40","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref42","article-title":"The sjtu x-lance lab system for cnsrc 2022","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2206.11699"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"}],"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\/10832140.pdf?arnumber=10832140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:25Z","timestamp":1737398365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832140","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}