{"id":"https://openalex.org/W2950105263","doi":"https://doi.org/10.21437/interspeech.2019-1399","title":"Large-Scale Speaker Diarization of Radio Broadcast Archives","display_name":"Large-Scale Speaker Diarization of Radio Broadcast Archives","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2950105263","doi":"https://doi.org/10.21437/interspeech.2019-1399","mag":"2950105263"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.07955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004568334","display_name":"Emre Y\u0131lmaz","orcid":"https://orcid.org/0000-0001-7466-3358"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Emre Y\u0131lmaz","raw_affiliation_strings":["National University of Singapore,"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062952705","display_name":"Adem Derinel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adem Derinel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063459528","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0003-0650-9521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042937911","display_name":"Henk van den Heuvel","orcid":"https://orcid.org/0000-0003-2064-0630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henk van den Heuvel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057092051","display_name":"Niko Br\u00fcmmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Brummer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055712584","display_name":"David A. van Leeuwen","orcid":"https://orcid.org/0000-0001-9704-6141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David A. van Leeuwen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004568334"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05434244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9929999709129333,"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":0.9793999791145325,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9452967643737793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7403537034988403},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.7352451086044312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6654065251350403},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.584885835647583},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5612596273422241},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5325310230255127},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5151252150535583},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.11815264821052551}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9452967643737793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7403537034988403},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7352451086044312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6654065251350403},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.584885835647583},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5612596273422241},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5325310230255127},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5151252150535583},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.11815264821052551},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.07955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07955","pdf_url":"https://arxiv.org/pdf/1906.07955","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"mag:2950105263","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.07955","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.07955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.07955","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.07955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07955","pdf_url":"https://arxiv.org/pdf/1906.07955","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W76945434","https://openalex.org/W1482605500","https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W1965819578","https://openalex.org/W2052269122","https://openalex.org/W2063511145","https://openalex.org/W2081074144","https://openalex.org/W2088234478","https://openalex.org/W2110023316","https://openalex.org/W2117671523","https://openalex.org/W2121812409","https://openalex.org/W2142333570","https://openalex.org/W2150769028","https://openalex.org/W2290689761","https://openalex.org/W2345986601","https://openalex.org/W2346457055","https://openalex.org/W2463927909","https://openalex.org/W2482731677","https://openalex.org/W2512355221","https://openalex.org/W2620757702","https://openalex.org/W2638067502","https://openalex.org/W2745909600","https://openalex.org/W2748488820","https://openalex.org/W2883989418","https://openalex.org/W2890964092","https://openalex.org/W2964209893","https://openalex.org/W3005347330"],"related_works":["https://openalex.org/W1549221042","https://openalex.org/W3008107337","https://openalex.org/W2063511145","https://openalex.org/W2463927909","https://openalex.org/W2057668940","https://openalex.org/W2774196182","https://openalex.org/W2144375099","https://openalex.org/W140455780","https://openalex.org/W2044525818","https://openalex.org/W67702164","https://openalex.org/W2103360771","https://openalex.org/W2407688633","https://openalex.org/W2901404901","https://openalex.org/W2398046462","https://openalex.org/W1975884129","https://openalex.org/W3016234652","https://openalex.org/W2166467513","https://openalex.org/W2072632448","https://openalex.org/W1616200970","https://openalex.org/W2805503960"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"initial":[4],"efforts":[5],"to":[6,61,70,96,136,185],"build":[7],"a":[8,17,109,127,154],"large-scale":[9,44,119],"speaker":[10,52,59,72,89,129,139,148,165,168],"diarization":[11,45,53],"(SD)":[12],"and":[13,57,113,122,177],"identification":[14,90],"system":[15,131,150],"on":[16,141,153,172],"recently":[18,110],"digitized":[19],"radio":[20],"broadcast":[21],"archive":[22,159,180],"from":[23,79],"the":[24,71,80,97,101,124,158,178,187,193],"Netherlands":[25],"which":[26,160],"has":[27],"more":[28],"than":[29],"6500":[30],"audio":[31],"tapes":[32],"with":[33,134,164],"3000":[34],"hours":[35],"of":[36,74,126,146,157,189,195],"Frisian-Dutch":[37],"speech":[38,84,196],"recorded":[39],"between":[40],"1950-2016.":[41],"The":[42,144,167],"employed":[43],"scheme":[46],"involves":[47],"two":[48],"stages:":[49],"(1)":[50],"tape-level":[51],"providing":[54],"pseudo-speaker":[55],"identities":[56],"(2)":[58],"linking":[60,92,130,149,169],"relate":[62],"pseudo-speakers":[63,98],"appearing":[64,77],"in":[65,192],"multiple":[66],"tapes.":[67],"Having":[68],"access":[69],"models":[73],"several":[75],"frequently":[76],"speakers":[78,95],"previously":[81],"collected":[82],"FAME!":[83],"corpus,":[85],"we":[86,107],"further":[87],"perform":[88],"by":[91],"these":[93],"known":[94],"identified":[99],"at":[100],"first":[102],"stage.":[103],"In":[104],"this":[105,142,147,173],"work,":[106],"present":[108],"created":[111],"longitudinal":[112],"multilingual":[114],"SD":[115,120],"corpus":[116],"designed":[117],"for":[118],"research":[121],"evaluate":[123],"performance":[125,145,170],"new":[128],"using":[132],"x-vectors":[133],"PLDA":[135],"quantify":[137,186],"cross-tape":[138],"similarity":[140],"corpus.":[143],"is":[151,161,183],"evaluated":[152],"small":[155],"subset":[156,174],"manually":[162],"annotated":[163],"information.":[166],"reported":[171],"(53":[175],"hours)":[176,182],"whole":[179],"(3000":[181],"compared":[184],"impact":[188],"scaling":[190],"up":[191],"amount":[194],"data.":[197]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
