{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:47:01Z","timestamp":1765039621386},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747450","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8367-8371","source":"Crossref","is-referenced-by-count":12,"title":["Multi-Scale Speaker Embedding-Based Graph Attention Networks For Speaker Diarisation"],"prefix":"10.1109","author":[{"given":"Youngki","family":"Kwon","sequence":"first","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hee-Soo","family":"Heo","sequence":"additional","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jee-Weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bong-Jin","family":"Lee","sequence":"additional","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref32","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref30","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","year":"2016","author":"loshchilov","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-149"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref12","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-566"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414057"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-993"},{"article-title":"Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks","year":"2021","author":"jung","key":"ref18"},{"key":"ref19","article-title":"First dihard challenge evaluation plan","author":"ryant","year":"2018","journal-title":"Tech Rep"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414578"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref6","article-title":"GRAPH ATTENTION NETWORKS","author":"velickovic","year":"2018","journal-title":"Proc ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"article-title":"The bytedance speaker diarization system for the voxceleb speaker recognition challenge 2021","year":"2021","author":"wang","key":"ref5"},{"key":"ref8","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref7","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-448"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"article-title":"The third dihard diarization challenge","year":"2020","author":"ryant","key":"ref21"},{"article-title":"But system description for dihard speech diarization challenge 2019","year":"2019","author":"landini","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"article-title":"Ustc-nelslip system description for dihard-iii challenge","year":"2021","author":"wang","key":"ref25"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747450.pdf?arnumber=9747450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:12Z","timestamp":1660593912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747450","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}