{"id":"https://openalex.org/W2103360771","doi":"https://doi.org/10.1145/1877850.1877857","title":"Towards automatic speaker retrieval for large multimedia archives","display_name":"Towards automatic speaker retrieval for large multimedia archives","publication_year":2010,"publication_date":"2010-10-29","ids":{"openalex":"https://openalex.org/W2103360771","doi":"https://doi.org/10.1145/1877850.1877857","mag":"2103360771"},"language":"en","primary_location":{"id":"doi:10.1145/1877850.1877857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1877850.1877857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Automated information extraction in media production","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/A5111969286","display_name":"Marijn Huijbregts","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marijn Huijbregts","raw_affiliation_strings":["Radboud University Nijmegen, Nijmegen, Netherlands","Radboud University Nijmegen, Nijmegen, Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen, Nijmegen, Netherlands#TAB#","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055712584","display_name":"David A. van Leeuwen","orcid":"https://orcid.org/0000-0001-9704-6141"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David van Leeuwen","raw_affiliation_strings":["Radboud University Nijmegen, Nijmegen, Netherlands","Radboud University Nijmegen, Nijmegen, Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University Nijmegen, Nijmegen, Netherlands#TAB#","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111969286"],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":1.015,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77152654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8631626963615417},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.610670268535614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5341158509254456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45337483286857605},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4457491338253021},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.437056303024292},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4255700409412384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31344830989837646},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26434558629989624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631626963615417},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.610670268535614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5341158509254456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45337483286857605},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4457491338253021},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.437056303024292},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4255700409412384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31344830989837646},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26434558629989624},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1877850.1877857","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1877850.1877857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Automated information extraction in media production","raw_type":"proceedings-article"},{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/86077","is_oa":false,"landing_page_url":"http://hdl.handle.net/2066/86077","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 AIEMPro, 15 - 20. Firenze : ACM","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":15,"referenced_works":["https://openalex.org/W1558643924","https://openalex.org/W1559425193","https://openalex.org/W1582867372","https://openalex.org/W1855529031","https://openalex.org/W1876378865","https://openalex.org/W1987663579","https://openalex.org/W1997873121","https://openalex.org/W2063511145","https://openalex.org/W2144125830","https://openalex.org/W2170065313","https://openalex.org/W2338994564","https://openalex.org/W2561675875","https://openalex.org/W2805889152","https://openalex.org/W3129653033","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W2111874347","https://openalex.org/W3120512183","https://openalex.org/W2118860825","https://openalex.org/W1509309911","https://openalex.org/W2096510939","https://openalex.org/W2041797852","https://openalex.org/W1599425004","https://openalex.org/W1940231550"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,65,89],"discuss":[4],"the":[5,61],"challenges":[6],"of":[7,60,71,75,82,85,93],"scaling":[8],"a":[9,18,52,58,67,78,91],"speaker":[10,19,34,43],"retrieval":[11,20],"system":[12,21],"for":[13,22,47],"small":[14],"audiovisual":[15,48],"collections":[16],"towards":[17],"large":[23,32],"audio":[24],"(visual)":[25],"archives.":[26],"We":[27],"show":[28],"that":[29],"with":[30],"our":[31],"scale":[33],"diarization":[35],"approach":[36],"it":[37],"is":[38,55],"possible":[39],"to":[40,45],"perform":[41],"query-by-example":[42],"retrieval;":[44],"search":[46],"documents":[49],"in":[50],"which":[51],"particular":[53],"person":[54],"talking.":[56],"On":[57,77],"selection":[59],"ICSI":[62],"meeting":[63],"corpus":[64],"obtain":[66,90],"Mean":[68],"Average":[69],"Precision":[70],"0.49":[72],"and":[73],"precision-at-ten":[74,92],"0.70.":[76],"much":[79],"larger":[80],"archive":[81],"three":[83],"months":[84],"Dutch":[86],"broadcast":[87],"television":[88],"0.52.":[94]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
