{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:24:13Z","timestamp":1783787053539,"version":"3.55.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054017","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7604-7608","source":"Crossref","is-referenced-by-count":158,"title":["CN-Celeb: A Challenging Chinese Speaker Recognition Dataset"],"prefix":"10.1109","author":[{"given":"Y.","family":"Fan","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology,Key Laboratory of Transient Physics,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.W.","family":"Kang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L.T.","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.C.","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H.L.","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.T.","family":"Cheng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.Y.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Z.Y.","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y.Q.","family":"Cai","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep speaker feature learning for textindependent speaker verification","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1705 03670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","first-page":"93","article-title":"Ther DARPA speech recognition research database: specifications and status","author":"fisher","year":"1986","journal-title":"Proc DARPA Workshop on Speech Recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref15","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"arXiv preprint arXiv 1706 08612"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref17","article-title":"Retinaface: Singlestage dense face localisation in the wild","author":"deng","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","first-page":"531","article-title":"Probabilistic linear discriminant analysis","author":"ioffe","year":"2006","journal-title":"European Conference on Computer Vision"},{"key":"ref8","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref7","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3238-7"},{"key":"ref1","article-title":"Finding difficult speakers in automatic speaker recognition","author":"stoll","year":"2011","journal-title":"Ph D thesis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref23","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Workshop on Automatic Speech Recognition and Understanding"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054017.pdf?arnumber=9054017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:40:08Z","timestamp":1756154408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054017","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}