{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:04:28Z","timestamp":1761897868888},"reference-count":22,"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\/icassp49357.2023.10095589","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":["Improving Transformer-Based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads"],"prefix":"10.1109","author":[{"given":"Ye-Rin","family":"Jeoung","sequence":"first","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon-Young","family":"Yang","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeong-Hwan","family":"Choi","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref12","article-title":"Deep learning using rectified linear units (ReLU)","author":"agarap","year":"2018","journal-title":"arXiv 1803 08375"},{"key":"ref15","article-title":"NIST speaker recognition evaluation chronicles","author":"alvin","year":"2004","journal-title":"Proc Odyssey"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"journal-title":"The 2000 NIST Speaker Recognition Evaluation","year":"2001","author":"martin","key":"ref20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref22","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","author":"fiscus","year":"2007","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383555"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-064-8_8"},{"key":"ref19","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv 1510 08484 [cs]"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-362"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref9","first-page":"7124","article-title":"Pyannote. audio: neural building blocks for speaker diarization","author":"bredin","year":"2020","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2233724"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538700"},{"key":"ref6","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"}],"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\/10095589.pdf?arnumber=10095589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:32Z","timestamp":1700507312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095589","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}