{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:36:48Z","timestamp":1772303808586,"version":"3.50.1"},"reference-count":56,"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":"EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems","award":["Grant EP\/L016796\/1"],"award-info":[{"award-number":["Grant EP\/L016796\/1"]}]},{"name":"EPSRC Fellowship","award":["EP\/P001017\/1"],"award-info":[{"award-number":["EP\/P001017\/1"]}]}],"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.2021.3067161","type":"journal-article","created":{"date-parts":[[2021,3,18]],"date-time":"2021-03-18T19:56:20Z","timestamp":1616097380000},"page":"1479-1490","source":"Crossref","is-referenced-by-count":5,"title":["Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking of Fundamental Frequency"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5501-7799","authenticated-orcid":false,"given":"Aidan O. T.","family":"Hogg","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0757-5504","authenticated-orcid":false,"given":"Christine","family":"Evers","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8911-1601","authenticated-orcid":false,"given":"Alastair H.","family":"Moore","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8546-8013","authenticated-orcid":false,"given":"Patrick A.","family":"Naylor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.1445789"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682924"},{"key":"ref33","first-page":"29","article-title":"The fundamental frequency variation spectrum","author":"laskowski","year":"0","journal-title":"Proc Fonetik"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162800"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015089"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495590"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960640"},{"key":"ref28","first-page":"953","article-title":"Unvoiced speech segregation","volume":"5","author":"wang","year":"2006","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947582"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.759042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828321"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170046"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367063"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2006.354802"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947583"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517556"},{"key":"ref50","article-title":"Python code for overlapping speaker segmentation using MHT tracking of F0","author":"hogg","year":"2021"},{"key":"ref51","first-page":"7124","article-title":"Pyannote audio: Neural building blocks for speaker diarization","author":"bredin","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref56","first-page":"3587","article-title":"Pyannote metrics: A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems","author":"bredin","year":"0","journal-title":"Proc Conf Int Speech Commun Assoc"},{"key":"ref55","article-title":"Librosa\/librosa: 0.7.2","author":"mcfee","year":"2020"},{"key":"ref54","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/362342.362367"},{"key":"ref52","article-title":"VOICEBOX: A speech processing toolbox for MATLAB","author":"brookes","year":"1997"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-056-4"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","article-title":"Speaker diarization: A review of recent research","volume":"20","author":"mir\u00f3","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref40","first-page":"381","article-title":"Analysis of phonetic dependence of segmentation errors in speaker diarization","author":"mcknight","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639171"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2008.103"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77383-4_54"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953192"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-65"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479804"},{"key":"ref4","article-title":"Speech segmentation and speaker diarisation for transcription and translation","author":"sinclair","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2990485"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4634018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.06.017"},{"key":"ref8","article-title":"Multichannel overlapping speaker segmentation using multiple hypothesis tracking of acoustic and spatial features","author":"hogg","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","first-page":"1359","article-title":"Observations on overlap: Findings and implications for automatic processing of multi-party conversation","author":"shriberg","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937185"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26061-3_26"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81926-1"},{"key":"ref48","first-page":"424","article-title":"A new algorithm for the maximum-weight clique problem","volume":"8","author":"\u00f6sterg\u00e5rd","year":"2001","journal-title":"Nordic J Comput"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88063-9_15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1979.1102177"},{"key":"ref41","article-title":"TIMIT acoustic-phonetic continuous speech corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium (LDC)"},{"key":"ref44","author":"blackman","year":"1998","journal-title":"Design and Analysis of Modern Tracking Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2017.1244"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09381673.pdf?arnumber=9381673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:57Z","timestamp":1652194437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9381673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3067161","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}