{"id":"https://openalex.org/W2400927397","doi":"https://doi.org/10.21437/interspeech.2011-732","title":"Investigation of cross-show speaker diarization","display_name":"Investigation of cross-show speaker diarization","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2400927397","doi":"https://doi.org/10.21437/interspeech.2011-732","mag":"2400927397"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-732","doi":"https://doi.org/10.21437/interspeech.2011-732","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-732","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2011","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101428618","display_name":"Qian Yang","orcid":"https://orcid.org/0000-0002-6552-7482","observed_orcids":["https://orcid.org/0000-0002-6552-7482"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067","observed_orcids":["https://orcid.org/0000-0003-4163-6067"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028","observed_orcids":["https://orcid.org/0000-0002-9809-7028"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1173,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89195884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2925","last_page":"2928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.98580002784729,"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":0.98580002784729,"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":0.008899999782443047,"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/T12031","display_name":"Speech and dialogue systems","score":0.002300000051036477,"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/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.6510000228881836},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.4650000035762787},{"id":"https://openalex.org/keywords/t-norms","display_name":"t-norms","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9373551607131958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734683513641357},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5445050597190857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5432528257369995},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5003819465637207},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4344404339790344},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4011722207069397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3681769371032715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-732","doi":"https://doi.org/10.21437/interspeech.2011-732","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-732","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W106647055","https://openalex.org/W115846232","https://openalex.org/W163811496","https://openalex.org/W1485877426","https://openalex.org/W1855529031","https://openalex.org/W2041823554","https://openalex.org/W2052269122","https://openalex.org/W2078953162","https://openalex.org/W2101025008","https://openalex.org/W2149220986","https://openalex.org/W2169165592","https://openalex.org/W2404175974","https://openalex.org/W2405439032","https://openalex.org/W2405472765","https://openalex.org/W2595741664"],"related_works":["https://openalex.org/W7095330699","https://openalex.org/W2404175974","https://openalex.org/W2405981216","https://openalex.org/W2493131962","https://openalex.org/W2399732698","https://openalex.org/W2396834488","https://openalex.org/W2621983742","https://openalex.org/W2004709066","https://openalex.org/W4296070207","https://openalex.org/W2290892587"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,10,15,57,121,134],"cross-show":[3,41,77,122,140,150],"diarization":[4,42,78,141],"is":[5,93],"to":[6,27],"index":[7],"speech":[8],"segments":[9],"speakers":[11,23],"from":[12],"a":[13,55],"set":[14,56],"shows,":[16],"with":[17,30,73],"the":[18,31,51,64,67,70,83,132,135,143],"particular":[19],"challenge":[20],"that":[21],"reappearing":[22],"across":[24],"shows":[25,99,154],"have":[26],"be":[28],"labeled":[29],"same":[32],"speaker":[33,148],"identity.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,112],"introduce":[39],"three":[40,52,65],"systems":[43,53],"namely":[44],"Global-BIC-Seg,":[45],"Global-BIC-Cluster,":[46],"and":[47,75,85,98,115,126],"Incremental.":[48],"We":[49,129],"compared":[50],"on":[54,82,108,124,139],"46":[58],"English":[59],"scientific":[60],"podcast":[61,153],"shows.":[62],"Among":[63],"systems,":[66],"Global-BIC-Cluster":[68],"achieves":[69],"best":[71],"performance":[72],"15.53%":[74],"13.21%":[76],"error":[79],"rate":[80],"(DER)":[81],"dev":[84,125],"test":[86,127],"set,":[87],"respectively.":[88],"However,":[89],"an":[90],"incremental":[91,110,144],"approach":[92],"more":[94],"practical":[95],"since":[96],"data":[97],"are":[100],"typically":[101],"collected":[102],"over":[103],"time.":[104],"By":[105],"applying":[106],"T-Norm":[107],"our":[109],"system,":[111],"obtain":[113],"13.18%":[114],"10.97%":[116],"relative":[117],"improvements":[118],"in":[119],"terms":[120],"DER":[123],"set.":[128],"also":[130],"investigate":[131],"impact":[133],"show":[136],"processing":[137],"order":[138],"for":[142],"system.":[145],"Index":[146],"Terms:":[147],"diarization,":[149,151],"conversational":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
