{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T18:06:22Z","timestamp":1719943582542},"reference-count":26,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61101160, 61271314, 61301300, 61401161, 61571192"],"award-info":[{"award-number":["61101160, 61271314, 61301300, 61401161, 61571192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005015","name":"South China University of Technology, China","doi-asserted-by":"crossref","award":["2015ZZ102, 2015ZM145, 2015ZM143"],"award-info":[{"award-number":["2015ZZ102, 2015ZM145, 2015ZM143"]}],"id":[{"id":"10.13039\/501100005015","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology in Guangzhou, China","award":["2013J2200070"],"award-info":[{"award-number":["2013J2200070"]}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"crossref","award":["2014A050503022, 2015A010103006, 2015A030313600, 2015A010103003"],"award-info":[{"award-number":["2014A050503022, 2015A010103006, 2015A030313600, 2015A010103003"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Foundation of China Scholarship Council","award":["201208440078"],"award-info":[{"award-number":["201208440078"]}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1016\/j.csl.2016.09.002","type":"journal-article","created":{"date-parts":[[2016,9,17]],"date-time":"2016-09-17T15:05:48Z","timestamp":1474124748000},"page":"81-99","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Unsupervised classification of speaker roles in multi-participant conversational speech"],"prefix":"10.1016","volume":"42","author":[{"given":"Yanxiong","family":"Li","sequence":"first","affiliation":[]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xue","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xinchao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jichen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xiaohui","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qianhua","family":"He","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2016.09.002_bib0010","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":"Anguera Miro","year":"2012","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"10.1016\/j.csl.2016.09.002_bib0015","series-title":"17th National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence","first-page":"679","article-title":"The rules behind roles: Identifying speaker role in radio broadcasts","author":"Barzilay","year":"2000"},{"key":"10.1016\/j.csl.2016.09.002_bib0020","series-title":"Interspeech","first-page":"1057","article-title":"Looking for relevant features for speaker role recognition","author":"Bigot","year":"2010"},{"key":"10.1016\/j.csl.2016.09.002_bib0025","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s11042-010-0609-9","article-title":"Detecting individual role using features extracted from speaker diarization results","volume":"60","author":"Bigot","year":"2012","journal-title":"Multimed. Tools Appl. Archiv"},{"key":"10.1016\/j.csl.2016.09.002_bib0030","series-title":"Slam@Interspeech","first-page":"66","article-title":"Speaker role recognition on TV broadcast documents","author":"Bigot","year":"2013"},{"key":"10.1016\/j.csl.2016.09.002_bib0035","series-title":"IEEE ICASSP","first-page":"5684","article-title":"Robust speaker turn role labeling of TV broadcast news shows","author":"Damnati","year":"2011"},{"key":"10.1016\/j.csl.2016.09.002_bib0040","series-title":"Pattern Classification","author":"Duda","year":"2000"},{"key":"10.1016\/j.csl.2016.09.002_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2013.07.007","article-title":"Characterizing and detecting spontaneous speech: application to speaker role recognition","volume":"56","author":"Dufour","year":"2014","journal-title":"Speech Commun"},{"key":"10.1016\/j.csl.2016.09.002_bib0050","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TASL.2011.2163395","article-title":"Transcribing meetings with the AMIDA systems","volume":"20","author":"Hain","year":"2012","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"10.1016\/j.csl.2016.09.002_bib0055","series-title":"IEEE ICASSP","first-page":"5322","article-title":"Unsupervised broadcast conversation speaker role labeling","author":"Hutchinson","year":"2010"},{"key":"10.1016\/j.csl.2016.09.002_bib0060","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1016\/j.sigpro.2007.11.017","article-title":"Speaker segmentation and clustering","volume":"88","author":"Kotti","year":"2008","journal-title":"Sign. Process"},{"key":"10.1016\/j.csl.2016.09.002_bib0065","series-title":"Interspeech","first-page":"76","article-title":"Boosting bonsai trees for efficient features combination: application to speaker role identification","author":"Laurent","year":"2014"},{"key":"10.1016\/j.csl.2016.09.002_bib0070","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1049\/iet-spr.2013.0340","article-title":"Fast speaker clustering using distance of feature matrix mean and adaptive convergence threshold","volume":"8","author":"Li","year":"2014","journal-title":"IET Sign. Process"},{"key":"10.1016\/j.csl.2016.09.002_bib0075","series-title":"International Conference on Audio, Language and Image Processing","first-page":"771","article-title":"Two-level approach for detecting non-lexical audio events in spontaneous speech","author":"Li","year":"2010"},{"key":"10.1016\/j.csl.2016.09.002_bib0080","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1016\/j.sigpro.2009.03.001","article-title":"Characteristics-based effective applause detection for meeting speech","volume":"89","author":"Li","year":"2009","journal-title":"Sign. Process"},{"key":"10.1016\/j.csl.2016.09.002_bib0085","series-title":"Human Language Technology Conference of the NAACL","first-page":"81","article-title":"Initial study on automatic identification of speaker role in broadcast news speech","author":"Liu","year":"2006"},{"key":"10.1016\/j.csl.2016.09.002_bib0090","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1016\/j.specom.2012.05.002","article-title":"A review on speaker diarization systems and approaches","volume":"54","author":"Moattar","year":"2012","journal-title":"Speech Commun"},{"key":"10.1016\/j.csl.2016.09.002_bib0095","author":"NIST"},{"key":"10.1016\/j.csl.2016.09.002_bib0100","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/MSP.2008.918023","article-title":"Speech segmentation and spoken document processing","volume":"25","author":"Ostendorf","year":"2008","journal-title":"IEEE Sign. Process. Mag"},{"key":"10.1016\/j.csl.2016.09.002_bib0105","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1109\/TMM.2011.2173927","article-title":"Automatic role recognition in multiparty conversations: an approach based on turn organization, prosody, and conditional random fields","volume":"14","author":"Salamin","year":"2012","journal-title":"IEEE Trans. Multimed"},{"key":"10.1016\/j.csl.2016.09.002_bib0110","series-title":"IEEE ICASSP","first-page":"5057","article-title":"Automatic speaker role labeling in AMI meetings: recognition of formal and social roles","author":"Sapru","year":"2012"},{"key":"10.1016\/j.csl.2016.09.002_bib0115","series-title":"IEEE ICASSP","first-page":"7741","article-title":"Where are the challenges in speaker diarization?","author":"Sinclair","year":"2013"},{"key":"10.1016\/j.csl.2016.09.002_bib0120","series-title":"IEEE ICASSP. IEEE","first-page":"4982","article-title":"Speaker diarization system for RT07 and RT09 meeting room audio","author":"Sun","year":"2010"},{"key":"10.1016\/j.csl.2016.09.002_bib0125","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1109\/TMM.2007.902882","article-title":"Speakers role recognition in multiparty audio recordings using social network analysis and duration distribution modeling","volume":"9","author":"Vinciarelli","year":"2007","journal-title":"IEEE Trans. Multimed"},{"key":"10.1016\/j.csl.2016.09.002_bib0130","series-title":"IEEE ICASSP","first-page":"5556","article-title":"Automatic identification of speaker role and agreement\/disagreement in broadcast conversation","author":"Wang","year":"2011"},{"key":"10.1016\/j.csl.2016.09.002_bib0135","series-title":"IEEE ICASSP","first-page":"96","article-title":"Information bottleneck based speaker diarization of meetings using non-speech as side information","author":"Yella","year":"2014"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230816302728?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230816302728?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T01:36:14Z","timestamp":1589679374000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230816302728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":26,"alternative-id":["S0885230816302728"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2016.09.002","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2017,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unsupervised classification of speaker roles in multi-participant conversational speech","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2016.09.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2016 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}