{"id":"https://openalex.org/W2162627003","doi":"https://doi.org/10.1109/tasl.2009.2024730","title":"BIC-Based Speaker Segmentation Using Divide-and-Conquer Strategies With Application to Speaker Diarization","display_name":"BIC-Based Speaker Segmentation Using Divide-and-Conquer Strategies With Application to Speaker Diarization","publication_year":2009,"publication_date":"2009-06-10","ids":{"openalex":"https://openalex.org/W2162627003","doi":"https://doi.org/10.1109/tasl.2009.2024730","mag":"2162627003"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2024730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2024730","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100883805","display_name":"Shih-Sian Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Sian Cheng","raw_affiliation_strings":["Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113498483","display_name":"Hsin-Chia Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Chia Fu","raw_affiliation_strings":["Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100883805"],"corresponding_institution_ids":["https://openalex.org/I148366613","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":7.6586,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97326808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"141","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9980999827384949,"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":0.8293781280517578},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7742705345153809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537425756454468},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.6373451948165894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5156201720237732},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.5125126838684082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.480035662651062},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.46208876371383667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4363930821418762},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4226738214492798},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4117283821105957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14158689975738525}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8293781280517578},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7742705345153809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537425756454468},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.6373451948165894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5156201720237732},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.5125126838684082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.480035662651062},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.46208876371383667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4363930821418762},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4226738214492798},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4117283821105957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14158689975738525},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2009.2024730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2024730","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.2082","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.2082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/referencias/Cheng_BIC-based.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W24669943","https://openalex.org/W91662920","https://openalex.org/W125260059","https://openalex.org/W140783384","https://openalex.org/W169282553","https://openalex.org/W200199050","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1562115776","https://openalex.org/W1827418370","https://openalex.org/W1924751832","https://openalex.org/W1968491588","https://openalex.org/W2038086080","https://openalex.org/W2041823554","https://openalex.org/W2044591814","https://openalex.org/W2047555270","https://openalex.org/W2052269122","https://openalex.org/W2063415950","https://openalex.org/W2075662881","https://openalex.org/W2104353650","https://openalex.org/W2110783210","https://openalex.org/W2113386290","https://openalex.org/W2117956188","https://openalex.org/W2119979862","https://openalex.org/W2131981197","https://openalex.org/W2137197207","https://openalex.org/W2143555316","https://openalex.org/W2144345993","https://openalex.org/W2151299225","https://openalex.org/W2159591770","https://openalex.org/W2159937480","https://openalex.org/W2166980079","https://openalex.org/W2168175751","https://openalex.org/W2171373074","https://openalex.org/W3141324706","https://openalex.org/W6603704010","https://openalex.org/W6606811552","https://openalex.org/W6608100561","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6640250534","https://openalex.org/W6681377254","https://openalex.org/W7009185688"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2119836628","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2157299333"],"abstract_inverted_index":{"In":[0,119],"this":[1,128],"paper,":[2],"we":[3,121],"propose":[4],"three":[5,59],"divide-and-conquer":[6],"approaches":[7,16,57,105,125],"for":[8],"Bayesian":[9],"information":[10],"criterion":[11],"(BlC)-based":[12],"speaker":[13,18,89,132],"segmentation.":[14],"The":[15,99,135],"detect":[17],"changes":[19],"by":[20,82],"recursively":[21,31],"partitioning":[22],"a":[23,46,140],"large":[24],"analysis":[25,86],"window":[26,74],"into":[27],"two":[28,36,51,94],"sub-windows":[29],"and":[30,65,76,78,87,109],"verifying":[32],"the":[33,103,115,123,131],"merging":[34],"of":[35,50],"adjacent":[37],"audio":[38,52],"segments":[39],"using":[40],"Delta":[41],"<i":[42],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">BIC</i>":[44],",":[45],"widely-adopted":[47],"distance":[48],"measure":[49],"segments.":[53],"We":[54],"compare":[55],"our":[56],"to":[58,130,146],"popular":[60],"distance-based":[61,117],"approaches,":[62],"namely,":[63],"Chen":[64],"Gopalakrishnan's":[66],"window-growing-based":[67],"approach,":[68,75,81],"Siegler":[69],"et":[70],"al.'s":[71],"fixed-size":[72],"sliding":[73],"Delacourt":[77],"Wellekens's":[79],"DISTBIC":[80],"performing":[83],"computational":[84],"cost":[85],"conducting":[88],"change":[90],"detection":[91],"experiments":[92],"on":[93],"broadcast":[95],"news":[96],"data":[97],"sets.":[98],"results":[100,137],"show":[101,138],"that":[102,139],"proposed":[104],"are":[106],"more":[107,141],"efficient":[108],"achieve":[110],"higher":[111],"segmentation":[112,124,143],"accuracy":[113],"than":[114],"compared":[116],"approaches.":[118],"addition,":[120],"apply":[122],"discussed":[126],"in":[127],"paper":[129],"diarization":[133,148],"task.":[134],"experiment":[136],"effective":[142],"approach":[144],"leads":[145],"better":[147],"accuracy.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}