{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:44:21Z","timestamp":1777567461934,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414578","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7173-7177","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Scale Speaker Diarization with Neural Affinity Score Fusion"],"prefix":"10.1109","author":[{"given":"Tae Jin","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manoj","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi-scale aggregation using feature pyramid module for text-independent speaker verification","author":"jung","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682712"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-277","article-title":"The majority wins: a method for combining speaker diarization systems","author":"huijbregts","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref13","article-title":"System output combination for improved speaker diarization","author":"bozonnet","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.1077"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659701"},{"key":"ref17","article-title":"Callhome diarization recipe using x-vectors","author":"snyder","year":"2018","journal-title":"Github"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref19","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"Proceedings of the Workshop on Deep Learning in International Conference on Machine Learning ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref3","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","volume":"1997","author":"siegler","year":"1997","journal-title":"Proc DARPA Speech Recognition Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref2","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the bayesian information criterion","volume":"8","author":"chen","year":"1998","journal-title":"Proc DARPA Broadcast News Transcription and Understanding Workshop"},{"key":"ref9","article-title":"But system description for dihard speech diarization challenge 2019","author":"landini","year":"2019"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053952"},{"key":"ref22","article-title":"A comparison of neural network feature transforms for speaker diarization","author":"yella","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1903"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414578.pdf?arnumber=9414578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T03:25:58Z","timestamp":1672111558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414578","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}