{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:39Z","timestamp":1738128459293,"version":"3.33.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848831","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["EEND-EM: End-to-End Neural Speaker Diarization with EM-Network"],"prefix":"10.1109","author":[{"given":"Beom Jun","family":"Woo","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji Won","family":"Yoon","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Artificial Intelligence,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min Hyun","family":"Han","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan Yeong","family":"Moon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462661"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3100682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2019.2961071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096449"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10097190"},{"key":"ref6","article-title":"End-to-end neural speaker diarization with permutation-free objectives","volume-title":"Interspeech","author":"Fujita","year":"2019"},{"key":"ref7","first-page":"296","article-title":"End-to-end neural speaker diarization with self-attention","volume-title":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Fujita"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3162080"},{"volume-title":"Target speaker voice activity detection with transformers and its integration with end-to-end neural diarization","year":"2022","author":"Wang","key":"ref9"},{"volume-title":"Speaker overlap-aware neural diarization for multi-party meeting analysis","author":"Du","key":"ref10","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.505"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"volume-title":"Eend-ss: Joint end-to-end neural speaker diarization and speech separation for flexible number of speakers","year":"2022","author":"Maiti","key":"ref12"},{"volume-title":"Used: Universal speaker extraction and diarization","year":"2024","author":"Ao","key":"ref13"},{"key":"ref14","volume-title":"Em-network: Oracle guided self-distillation for sequence learning","volume":"abs\/2306.10058","author":"Yoon","year":"2023"},{"volume-title":"Librimix: An open-source dataset for generalizable speech separation","year":"2020","author":"Cosentino","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178964"},{"volume-title":"Wham!: Extending speech separation to noisy environments","year":"2019","author":"Wichern","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848831.pdf?arnumber=10848831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:21:56Z","timestamp":1738045316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848831","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}