{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:55:58Z","timestamp":1774162558798,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF","award":["IIS 19-10 319"],"award-info":[{"award-number":["IIS 19-10 319"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2020.3040626","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T21:46:11Z","timestamp":1606340771000},"page":"324-333","source":"Crossref","is-referenced-by-count":8,"title":["Auxiliary Networks for Joint Speaker Adaptation and Speaker Change Detection"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3754-1156","authenticated-orcid":false,"given":"Leda","family":"Sari","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-2893","authenticated-orcid":false,"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7573-0620","authenticated-orcid":false,"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472689"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472692"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref30","first-page":"6286","article-title":"Pre-training of speaker embeddings for low-latency speaker change detection in broadcast news","author":"sar?","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"arXiv 1211 3711"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref34","first-page":"769","article-title":"Learning speaker aware offsets for speaker adaptation of neural networks","volume":"2019","author":"sar?","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref27","first-page":"1031","article-title":"Fast speaker change detection for broadcast news transcription and indexing","author":"liu","year":"0","journal-title":"Proc 6th Eur Conf Speech Commun Technol"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref1","first-page":"109","article-title":"Improved feature processing for deep neural networks","author":"rath","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref26","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the bayesian information criterion","volume":"8","author":"chen","year":"0","journal-title":"Proc DARPA Broadcast News Transcription Understanding Workshop"},{"key":"ref25","first-page":"97","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","author":"siegler","year":"0","journal-title":"Proc DARPA Speech Recognit Workshop"},{"key":"ref50","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Sclite scoring package version 1.5","author":"fiscus","year":"1998"},{"key":"ref54","article-title":"Callhome Diarization Xvector Model","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref52","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-460"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2022"},{"key":"ref12","article-title":"Speaker adaptation with an auxiliary network","author":"sar?","year":"2018","journal-title":"Proc Mach Learn Speech Lang Process Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541103"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref17","first-page":"7384","article-title":"Unsupervised speaker adaptation using attention-based speaker memory for end-to-end ASR","author":"sar?","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003844"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","article-title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition","volume":"22","author":"xue","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref46","article-title":"1997 English Broadcast News Speech (HUB4)","year":"0"},{"key":"ref45","article-title":"1996 English Broadcast News Speech (HUB4)","year":"0"},{"key":"ref48","article-title":"2000 HUB5 English Evaluation Speech","year":"0"},{"key":"ref47","article-title":"Switchboard-1 Release 2","year":"0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078608"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-65"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9289074\/9271936-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09271936.pdf?arnumber=9271936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:21Z","timestamp":1649444061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9271936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3040626","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}