{"id":"https://openalex.org/W1991048564","doi":"https://doi.org/10.1145/1322192.1322254","title":"On-line multi-modal speaker diarization","display_name":"On-line multi-modal speaker diarization","publication_year":2007,"publication_date":"2007-11-12","ids":{"openalex":"https://openalex.org/W1991048564","doi":"https://doi.org/10.1145/1322192.1322254","mag":"1991048564"},"language":"en","primary_location":{"id":"doi:10.1145/1322192.1322254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","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/A5053745317","display_name":"A. Noulas","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Athanasios Noulas","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349937","display_name":"Ben Kr\u00f6se","orcid":"https://orcid.org/0000-0003-1237-0618"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ben J. A. Krose","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053745317"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":5.3126,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95288907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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":0.8140177726745605},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7464017868041992},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6750219464302063},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.613007128238678},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5004842281341553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4384792149066925},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.42643940448760986},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4065552353858948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059428870677948},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3271982669830322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140177726745605},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7464017868041992},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6750219464302063},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.613007128238678},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5004842281341553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4384792149066925},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.42643940448760986},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4065552353858948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059428870677948},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3271982669830322},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1322192.1322254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/161eb1a8-111f-426f-8b53-abe4ef04aa4f","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/online-multimodal-speaker-diarization(161eb1a8-111f-426f-8b53-abe4ef04aa4f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Noulas, A & Kr\u00f6se, B J A 2007, On-line Multi-Modal Speaker Diarization. in Proceedings of International Conference on Multimodal Interfaces '07. Nagoya, Japan, pp. 350-358.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/161eb1a8-111f-426f-8b53-abe4ef04aa4f","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/online-multimodal-speaker-diarization(161eb1a8-111f-426f-8b53-abe4ef04aa4f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Noulas, A & Kr\u00f6se, B J A 2007, On-line Multi-Modal Speaker Diarization. in Proceedings of International Conference on Multimodal Interfaces '07. Nagoya, Japan, pp. 350-358.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/161eb1a8-111f-426f-8b53-abe4ef04aa4f","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/online-multimodal-speaker-diarization(161eb1a8-111f-426f-8b53-abe4ef04aa4f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of International Conference on Multimodal Interfaces '07, 350 - 358","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W10842935","https://openalex.org/W1482605500","https://openalex.org/W1567497459","https://openalex.org/W1762918658","https://openalex.org/W1986647142","https://openalex.org/W2025653905","https://openalex.org/W2109124605","https://openalex.org/W2110413319","https://openalex.org/W2118781513","https://openalex.org/W2130102735","https://openalex.org/W2133081131","https://openalex.org/W2151103935","https://openalex.org/W2156255174","https://openalex.org/W2157145630","https://openalex.org/W2160337655","https://openalex.org/W2492794003","https://openalex.org/W3160125816","https://openalex.org/W6677291441"],"related_works":["https://openalex.org/W2206035908","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","https://openalex.org/W2997340161"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,26,31],"novel":[4],"framework":[5],"that":[6],"utilizes":[7],"multi-modal":[8,33],"information":[9],"to":[10,19,30,45],"achieve":[11,20],"speaker":[12],"diarization.":[13],"We":[14,23,40,63],"use":[15],"dynamic":[16],"Bayesian":[17],"networks":[18],"on-line":[21],"results.":[22],"progress":[24],"from":[25,75],"simple":[27,61],"observation":[28],"model":[29,53],"complex":[32,52],"one":[34],"as":[35],"more":[36],"data":[37],"becomes":[38],"available.":[39],"present":[41,64],"an":[42],"efficient":[43],"way":[44],"guide":[46],"the":[47,51,55,60,65],"learning":[48],"procedure":[49],"of":[50],"using":[54],"early":[56],"results":[57,66],"achieved":[58,67],"with":[59],"model.":[62],"in":[68],"various":[69],"real-world":[70],"situations,":[71],"including":[72],"videos":[73],"coming":[74],"webcameras,":[76],"human":[77],"computer":[78],"interaction":[79],"and":[80],"video":[81],"conferences.":[82]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
