{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:12:02Z","timestamp":1755839522298,"version":"3.28.0"},"reference-count":33,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094824","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":["Neural Diarization with Non-Autoregressive Intermediate Attractors"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Fujita","sequence":"first","affiliation":[{"name":"LINE Corporation,Japan"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"LINE Corporation,Japan"}]},{"given":"Robin","family":"Scheibler","sequence":"additional","affiliation":[{"name":"LINE Corporation,Japan"}]},{"given":"Yusuke","family":"Kida","sequence":"additional","affiliation":[{"name":"LINE Corporation,Japan"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref14","first-page":"4930","article-title":"Speaker diarization using deep neural network embed-dings","author":"garcia-romero","year":"2017","journal-title":"ICASSP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref30","first-page":"241","article-title":"Permutation in-variant training of deep models for speaker-independent multi-talker speech separation","author":"yu","year":"2017","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref32"},{"key":"ref2","first-page":"2011","article-title":"Acoustic beam-forming for speaker diarization of meetings","volume":"15","author":"anguera","year":"2007","journal-title":"IEEE Trans on ASLP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref18","first-page":"1","article-title":"But system description for the third dihard speech diarization challenge","author":"landini","year":"2021","journal-title":"Proceedings available at Di-hard Challenge Github"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1909"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538700"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"year":"0","key":"ref4","article-title":"2000 NIST Speaker Recognition Evaluation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref6","first-page":"212","article-title":"Overlap in meetings: ASR effects and analysis by dialog factors, speakers, and collection site","author":"\u00e7etin","year":"2006","journal-title":"MLMI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"}],"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\/10094824.pdf?arnumber=10094824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:52Z","timestamp":1700507212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094824","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}