{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:44:33Z","timestamp":1730231073967,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003803","name":"University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096814","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Speaker Recognition with Two-Step Multi-Modal Deep Cleansing"],"prefix":"10.1109","author":[{"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR,Singapore"}]},{"given":"Zhan","family":"Shi","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00342"},{"key":"ref12","first-page":"4308","article-title":"Superloss: A generic loss for robust curriculum learning","volume":"33","author":"castells","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746294"},{"key":"ref14","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"arpit","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref30","article-title":"MUSAN: A music, speech, and noise corpus","volume":"abs 1510 8484","author":"snyder","year":"2015","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659567"},{"key":"ref1","first-page":"3317","article-title":"Joint application of speech and speaker recognition for automation and security in smart home","author":"lee","year":"2011","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980095"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref19","first-page":"605","article-title":"Hlt-nus submission for 2019 nist multimedia speaker recognition evaluation","author":"das","year":"2020","journal-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"journal-title":"IEEE Transactions on Multimedia","article-title":"Audio-visual tracking of concurrent speakers","year":"2021","author":"qian","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref23","first-page":"6194","article-title":"A multi-view approach to audio-visual speaker verification","author":"sar?","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.254"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683477"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00297"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref8","first-page":"2977","article-title":"In defence of metric learning for speaker recognition","author":"chung","year":"2020","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1570"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3091932"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref6","first-page":"3830","article-title":"ECAPA-TDNN: Emphasized Channel Attention, propagation and aggregation in TDNN based speaker verification","author":"desplanques","year":"2020","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096814.pdf?arnumber=10096814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:04:28Z","timestamp":1700507068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096814","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}