{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:04:07Z","timestamp":1761897847360,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023]]},"DOI":"10.1109\/taslp.2023.3244513","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T18:45:44Z","timestamp":1677264344000},"page":"1037-1049","source":"Crossref","is-referenced-by-count":3,"title":["QDM-SSD: Quality-Aware Dynamic Masking for Separation-Based Speaker Diarization"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0315-1042","authenticated-orcid":false,"given":"Shu-Tong","family":"Niu","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7680-6455","authenticated-orcid":false,"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"given":"Yu","family":"Hu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020\u20139"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"},{"article-title":"VoxSRC 2020: The second voxceleb speaker recognition challenge","year":"2020","author":"Nagrani","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"article-title":"First DIHARD challenge evaluation plan","year":"2018","author":"Ryant","key":"ref10"},{"article-title":"Second DIHARD challenge evaluation plan","year":"2019","author":"Ryant","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1208"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054251"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383602"},{"article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","year":"2020","author":"Fujita","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-235"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2558822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53547-0_25"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462505"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413933"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1629"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054577"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"article-title":"Separation guided speaker diarization in realistic mismatched conditions","year":"2021","author":"Niu","key":"ref47"},{"key":"ref48","first-page":"667","article-title":"A deep analysis of speech separation guided diarization under realistic conditions","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Fang","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746354"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-516"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-516"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6091"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00344"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_45"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-384"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref58","first-page":"1","article-title":"Voice activity detection","author":"Kola","year":"2011"},{"key":"ref59","first-page":"65","article-title":"Linguistic resources for effective, affordable, reusable speech-to-text","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Strassel","year":"2004"},{"article-title":"2000 Hub5 english evaluation speech LDC2002S09","year":"2002","author":"Consortium","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref62","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"year":"2009","key":"ref63","article-title":"The (RT-09) rich transcription meeting recognition evaluation plan"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955293"},{"key":"ref66","article-title":"BUT system description for the third DIHARD speech diarization challenge","volume-title":"Proc. 3rd DIHARD Speech Diarization Challenge Workshop","author":"Landini","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053317"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11267"},{"key":"ref70","first-page":"293","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","volume-title":"Proc. 9th Int. Conf. Spoken Lang. Process.","author":"etin","year":"2006"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682274"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10043677.pdf?arnumber=10043677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T04:58:23Z","timestamp":1712811503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10043677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3244513","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}