{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:46:29Z","timestamp":1773247589783,"version":"3.50.1"},"reference-count":71,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DoD"},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["1R01 MH114925-01"],"award-info":[{"award-number":["1R01 MH114925-01"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]}],"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.2021.3061885","type":"journal-article","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T21:03:31Z","timestamp":1614373411000},"page":"1204-1219","source":"Crossref","is-referenced-by-count":15,"title":["Meta-Learning With Latent Space Clustering in Generative Adversarial Network for Speaker Diarization"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0788-4158","authenticated-orcid":false,"given":"Monisankha","family":"Pal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manoj","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1010-065X","authenticated-orcid":false,"given":"Raghuveer","family":"Peri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4177-7487","authenticated-orcid":false,"given":"Tae Jin","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"So Hyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine","family":"Lord","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Somer","family":"Bishop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-6204","authenticated-orcid":false,"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-15"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00452"},{"key":"ref38","article-title":"Spectral clustering using deep neural networks","author":"shaham","year":"0","journal-title":"Proc Int Conf Learn Repesentations"},{"key":"ref33","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"key":"ref31","article-title":"Clustering with deep learning: Taxonomy and new methods","author":"aljalbout","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683393"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref36","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","author":"yang","year":"0","journal-title":"Proc ICML JMLR org"},{"key":"ref35","article-title":"A study of semi-supervised speaker diarization system using gan mixture model","author":"pal","year":"0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/423"},{"key":"ref60","article-title":"Precise recovery of latent vectors from generative adversarial networks","author":"lipton","year":"0","journal-title":"Proc Workshop track-ICLR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref63","article-title":"Speaker recognition in a multi-speaker environment","author":"martin","year":"0","journal-title":"Proc 17th Eur Conf Speech Commun Technol"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014610"},{"key":"ref64","article-title":"Second DIHARD challenge evaluation plan,” linguistic data consortium","author":"ryant","year":"2019"},{"key":"ref27","first-page":"6504","article-title":"Speaker diarization using latent space clustering in generative adversarial network","author":"pal","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref65","article-title":"The speed submission to DIHARD II: Contributions & lessons learned","author":"sahidullah","year":"0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1023\/A:1005592401947"},{"key":"ref29","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-016-2782-9"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2757"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref20","article-title":"Enhancements for audio-only diarization systems","author":"dimitriadis","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002085"},{"key":"ref21","article-title":"Links: A high-dimensional online clustering method","author":"mansfield","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053477"},{"key":"ref26","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"xie","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref50","first-page":"2982","article-title":"Meta-learning for short utterance speaker recognition with imbalance length pairs","author":"kye","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053251"},{"key":"ref59","first-page":"4088","article-title":"Triple generative adversarial nets","volume":"30","author":"li","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty563"},{"key":"ref57","first-page":"2234","article-title":"Improved techniques for training gans","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955293"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1109"},{"key":"ref54","first-page":"5767","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref53","first-page":"214","author":"arjovsky","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref52","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref40","article-title":"Discriminative neural clustering for speaker diarisation","author":"li","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-51"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref18","first-page":"2178","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1903"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref45","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"in Proc ICML Deep Learn Workshop"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3010"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2167240"},{"key":"ref41","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"Proc Int Conf Learn Repesentations"},{"key":"ref44","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref43","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"0","journal-title":"Proc ICML"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09364728.pdf?arnumber=9364728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:02Z","timestamp":1652194442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9364728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3061885","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}