{"id":"https://openalex.org/W2118568685","doi":"https://doi.org/10.1109/icassp.2003.1202300","title":"Towards domain independent speaker clustering","display_name":"Towards domain independent speaker clustering","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2118568685","doi":"https://doi.org/10.1109/icassp.2003.1202300","mag":"2118568685"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202300","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007484629","display_name":"Y. Moh","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Y. Moh","raw_affiliation_strings":["Lehrstuhl fur Informatik VI Computer Science Department, RWTH-Aachen-University of Technology, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl fur Informatik VI Computer Science Department, RWTH-Aachen-University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083465496","display_name":"P. Nguyen","orcid":"https://orcid.org/0009-0007-9117-3570"},"institutions":[{"id":"https://openalex.org/I4210095956","display_name":"Panasonic (United States)","ror":"https://ror.org/00pvgrv63","country_code":"US","type":"company","lineage":["https://openalex.org/I1283155146","https://openalex.org/I4210095956"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Nguyen","raw_affiliation_strings":["Panasonic Speech Technology Laboratory (PSTL), Panasonic Technologies Company, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Panasonic Speech Technology Laboratory (PSTL), Panasonic Technologies Company, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I4210095956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111932064","display_name":"J.-C. Junqua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095956","display_name":"Panasonic (United States)","ror":"https://ror.org/00pvgrv63","country_code":"US","type":"company","lineage":["https://openalex.org/I1283155146","https://openalex.org/I4210095956"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.-C. Junqua","raw_affiliation_strings":["Panasonic Speech Technology Laboratory (PSTL), Panasonic Technologies Company, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Panasonic Speech Technology Laboratory (PSTL), Panasonic Technologies Company, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I4210095956"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.006,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.96252567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7967671155929565},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7907798886299133},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6178321838378906},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6062656044960022},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.573435366153717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5351335406303406},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49021345376968384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4761754870414734},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.4502677917480469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3558127284049988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967671155929565},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7907798886299133},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6178321838378906},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6062656044960022},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.573435366153717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5351335406303406},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49021345376968384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4761754870414734},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.4502677917480469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3558127284049988},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1202300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202300","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:129294","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/129294","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings / 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing : April 6- 10, 2003, Hong Kong Convention & Exhibition Center, Hong Kong / sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society<br/>2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, Peoples R China, 2003-04-06 - 2003-04-10","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1547083988","https://openalex.org/W2041823554","https://openalex.org/W2098559774","https://openalex.org/W2107617395","https://openalex.org/W2151299225","https://openalex.org/W2800394774","https://openalex.org/W3017143921","https://openalex.org/W6632910081","https://openalex.org/W6674694071","https://openalex.org/W6676027155"],"related_works":["https://openalex.org/W2141262306","https://openalex.org/W76945434","https://openalex.org/W2168175751","https://openalex.org/W1499900670","https://openalex.org/W1484181928","https://openalex.org/W2107617395","https://openalex.org/W2151299225","https://openalex.org/W2098559774","https://openalex.org/W2398758317","https://openalex.org/W2044591814","https://openalex.org/W3765491","https://openalex.org/W1482605500","https://openalex.org/W2620921085","https://openalex.org/W2156255174","https://openalex.org/W2118313846","https://openalex.org/W2041823554","https://openalex.org/W125260059","https://openalex.org/W106647055","https://openalex.org/W83866820","https://openalex.org/W119794901"],"abstract_inverted_index":{"Speaker":[0,41],"clustering":[1,26,42,94],"is":[2,43,95,115,128],"a":[3,37,45,75,89,118,140],"key":[4],"component":[5],"in":[6,36,60,154],"many":[7,56],"speech":[8],"processing":[9],"applications.":[10],"We":[11,158],"focus":[12],"on":[13,97,101,117,144,165],"Broadcast":[14],"News":[15],"meta":[16],"data":[17,170],"annotation":[18],"and":[19,32,63],"speaker":[20,25,93,137],"adaptation.":[21],"In":[22,78],"this":[23,79,155],"setting,":[24],"consists":[27],"of":[28,47,147],"identifying":[29],"who":[30],"spoke,":[31],"when":[33,64],"they":[34,65],"spoke":[35],"long":[38],"news":[39],"broadcast.":[40],"given":[44],"set":[46],"short":[48],"audio":[49,149],"segments.":[50,150],"Ideally,":[51],"it":[52],"will":[53],"discover":[54],"how":[55],"people":[57],"are":[58,66,152,159],"speaking":[59],"the":[61,148],"broadcast,":[62],"speaking.":[67],"The":[68,92,112,133],"same":[69],"problem":[70],"can":[71],"be":[72],"transposed":[73],"to":[74,161],"different":[76,169],"domain.":[77],"paper,":[80],"we":[81],"present":[82],"two":[83],"techniques":[84],"that":[85],"do":[86],"not":[87],"require":[88],"priori":[90],"training.":[91],"based":[96,116,143],"information":[98,120],"collected":[99],"solely":[100],"encountered":[102],"test":[103],"data.":[104],"They":[105],"aim":[106],"at":[107],"being":[108],"portable":[109],"across":[110,168],"domains.":[111],"first":[113],"method":[114],"Bayesian":[119],"criterion":[121],"(BIC),":[122],"with":[123],"single":[124],"full-covariance":[125],"Gaussians.":[126],"It":[127],"fairly":[129],"primitive":[130],"but":[131],"effective.":[132],"second":[134],"method,":[135],"called":[136],"triangulation,":[138],"constructs":[139],"coordinate":[141,156],"system":[142],"conditional":[145],"likelihoods":[146],"Clusters":[151],"located":[153],"system.":[157],"able":[160],"achieve":[162],"state-of-the-art":[163],"performance":[164],"NIST":[166],"evaluations":[167],"sets.":[171]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
