{"id":"https://openalex.org/W2124673517","doi":"https://doi.org/10.1109/icassp.2008.4518080","title":"Estimating the dominant person in multi-party conversations using speaker diarization strategies","display_name":"Estimating the dominant person in multi-party conversations using speaker diarization strategies","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2124673517","doi":"https://doi.org/10.1109/icassp.2008.4518080","mag":"2124673517"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518080","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061353073","display_name":"Hayley Hung","orcid":"https://orcid.org/0000-0001-9574-5395"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hayley Hung","raw_affiliation_strings":["IDIAP, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715214","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-1363-5318"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Department of Computer Science, University of California, Berkeley, USA","International Computer Science Institute, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012965551","display_name":"Daniel G\u00e1tica-P\u00e9rez","orcid":"https://orcid.org/0000-0001-5488-2182"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Gatica-Perez","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne, Switzerland","IDIAP, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2197","last_page":"2200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8280361890792847},{"id":"https://openalex.org/keywords/dominance","display_name":"Dominance (genetics)","score":0.7902389764785767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7156183123588562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5735111236572266},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5601866245269775},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5534011125564575},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46841946244239807},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.43938061594963074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3648661971092224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3348315358161926},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3255354166030884},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14207428693771362},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11353331804275513}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8280361890792847},{"id":"https://openalex.org/C151913843","wikidata":"https://www.wikidata.org/wiki/Q3454555","display_name":"Dominance (genetics)","level":3,"score":0.7902389764785767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156183123588562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5735111236572266},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5601866245269775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5534011125564575},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46841946244239807},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43938061594963074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3648661971092224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3348315358161926},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3255354166030884},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14207428693771362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11353331804275513},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp.2008.4518080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518080","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.2567","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.2567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~gatica/publications/HungHuangFriedlandGatica-icassp08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.7433","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.7433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2007/hung-idiap-rr-07-60.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.727.9458","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.727.9458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepage.tudelft.nl/3e2t5/hung-ICASSP-2008.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146058","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146058","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:146427","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146427","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146058","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/hung:rr07-60","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146058","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146058","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W187535091","https://openalex.org/W1967880820","https://openalex.org/W2110783210","https://openalex.org/W2124332251","https://openalex.org/W2125336414","https://openalex.org/W2133457618","https://openalex.org/W2165061375","https://openalex.org/W2338994564","https://openalex.org/W2560308376","https://openalex.org/W6659344013","https://openalex.org/W6678809451","https://openalex.org/W6684225735","https://openalex.org/W6730845448"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"In":[0,59],"this":[1,40],"paper,":[2],"we":[3,38,61,112,115],"apply":[4],"speaker":[5],"diarization":[6,133],"strategies":[7],"from":[8],"a":[9,21,94],"single":[10,95],"source":[11,71],"to":[12,74,79],"the":[13,17,84,100,118,126,131],"task":[14],"of":[15,87,104,125,128],"estimating":[16],"dominant":[18],"person":[19],"in":[20,41,108],"group":[22],"meeting.":[23],"Previous":[24],"work":[25],"has":[26],"shown":[27],"that":[28,114],"speaking":[29],"length":[30],"is":[31,51],"strongly":[32],"correlated":[33],"with":[34,121],"perceived":[35],"dominance.":[36],"Here":[37],"investigate":[39,62],"more":[42],"depth":[43],"by":[44],"considering":[45],"two":[46],"dominance":[47,80,110],"tasks":[48],"where":[49],"there":[50],"full":[52],"and":[53,67,70,93,130],"majority":[54],"agreement":[55],"amongst":[56],"ground-truth":[57],"annotators.":[58],"addition,":[60],"how":[63],"24":[64,105],"different":[65],"speed-up":[66],"algorithmic":[68],"strategies,":[69],"types":[72],"lead":[73],"interesting":[75],"outcomes":[76],"when":[77],"applied":[78],"estimation.":[81],"We":[82],"obtained":[83],"best":[85],"performance":[86],"77%":[88],"using":[89],"our":[90],"slowest":[91],"scheme":[92],"distant":[96],"microphone":[97],"(SDM).":[98],"Within":[99],"top":[101],"3":[102],"out":[103],"performing":[106],"experiments":[107],"both":[109],"tasks,":[111],"show":[113],"can":[116],"use":[117],"furthest":[119],"SDM,":[120],"no":[122],"prior":[123],"knowledge":[124],"number":[127],"speakers":[129],"fastest":[132],"scheme,":[134],"which":[135],"performs":[136],"1.3":[137],"times":[138],"faster":[139],"than":[140],"real-time.":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
