{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T14:51:46Z","timestamp":1787064706475,"version":"build-2736575974"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023280","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"641-646","source":"Crossref","is-referenced-by-count":9,"title":["Low-Latency Speech Separation Guided Diarization for Telephone Conversations"],"prefix":"10.1109","author":[{"given":"Giovanni","family":"Morrone","sequence":"first","affiliation":[{"name":"Università Politecnica delle Marche,Ancona,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Università Politecnica delle Marche,Ancona,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Serafini","sequence":"additional","affiliation":[{"name":"Università Politecnica delle Marche,Ancona,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrico","family":"Zovato","sequence":"additional","affiliation":[{"name":"PerVoice S.p.A.,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Brutti","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Squartini","sequence":"additional","affiliation":[{"name":"Università Politecnica delle Marche,Ancona,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2011.2125954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953094"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2019.2961071"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref8","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"Fujita","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2017.2726762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref13","article-title":"The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap","volume":"abs\/2102.01363","author":"Horiguchi","year":"2021","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"},{"key":"ref15","first-page":"7193","article-title":"BW-ED A-EEND: Streaming end-to-end neural speaker diarization for a variable number of speakers","volume-title":"ICASSP","author":"Han","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-708"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688178"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"ref22","first-page":"7284","article-title":"Continuous speech separation: Dataset and analy-sis","volume-title":"ICASSP","author":"Chen","year":"2020"},{"key":"ref23","article-title":"Conversational speech separation: an evaluation study for streaming applications","volume":"152","author":"Morrone","year":"2022","journal-title":"AES Convention"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref26","first-page":"667","article-title":"A deep analysis of speech separation guided diarization under realistic conditions","author":"Fang","year":"2021","journal-title":"APSIPA ASC"},{"key":"ref27","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"69","article-title":"The Fisher Cor-pus: A resource for the next generations of speech-to-text","volume":"4","author":"Cieri","year":"2004","journal-title":"LREC"},{"key":"ref29","volume-title":"2000 NIST Speaker Recognition Evaluation LDC2001S9","author":"Przybocki","year":"2001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref35","first-page":"5819","article-title":"Analysis of the BUT diarization system for Vox-Converse challenge","volume-title":"ICASSP","author":"Landini","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101306"},{"key":"ref37","volume-title":"Open Speech Language and Resources","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1673"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref40","volume-title":"md-eval.pl (Version 22) in SCTK (version 2.4.12)","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404842"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref43","article-title":"The Kaldi speech recognition toolkit","volume-title":"ASRU","author":"Povey","year":"2011"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023280.pdf?arnumber=10023280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T03:09:06Z","timestamp":1707793746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023280","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}