{"id":"https://openalex.org/W2056377860","doi":"https://doi.org/10.1142/s0218001412600117","title":"ONLINE SPEAKER DIARIZATION FOR MULTIMEDIA DATA RETRIEVAL ON MOBILE DEVICES","display_name":"ONLINE SPEAKER DIARIZATION FOR MULTIMEDIA DATA RETRIEVAL ON MOBILE DEVICES","publication_year":2012,"publication_date":"2012-11-26","ids":{"openalex":"https://openalex.org/W2056377860","doi":"https://doi.org/10.1142/s0218001412600117","mag":"2056377860"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001412600117","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001412600117","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5014783730","display_name":"Kyung-Mi Park","orcid":"https://orcid.org/0000-0002-7688-1567"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"KYUNG-MI PARK","raw_affiliation_strings":["Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046867197","display_name":"Jeong\u2010Sik Park","orcid":"https://orcid.org/0000-0002-4213-8775"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JEONG-SIK PARK","raw_affiliation_strings":["Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987030","display_name":"Jaehyun Bae","orcid":"https://orcid.org/0000-0002-7300-4518"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JAE-HYUN BAE","raw_affiliation_strings":["Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108235","display_name":"Yung\u2010Hwan Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"YUNG-HWAN OH","raw_affiliation_strings":["Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Computer Science Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014783730"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.3261,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83804539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"26","issue":"08","first_page":"1260011","last_page":"1260011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.8880916833877563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8583575487136841},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6965377330780029},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6242671012878418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5324813723564148},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.492277055978775},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4741508364677429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37333351373672485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3331044018268585}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8880916833877563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583575487136841},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6965377330780029},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6242671012878418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5324813723564148},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.492277055978775},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4741508364677429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37333351373672485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3331044018268585},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001412600117","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001412600117","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W9688279","https://openalex.org/W76945434","https://openalex.org/W1530770299","https://openalex.org/W1991048564","https://openalex.org/W2029687556","https://openalex.org/W2041823554","https://openalex.org/W2044591814","https://openalex.org/W2118313846","https://openalex.org/W2159591770","https://openalex.org/W2171373074","https://openalex.org/W2171700247","https://openalex.org/W2290695582","https://openalex.org/W2395619215","https://openalex.org/W2620921085"],"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/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,28],"detects":[2],"speaker":[3,11,27,99,155,167],"change":[4,156],"points":[5],"in":[6,59,145],"spoken":[7,87],"data":[8,31,88],"and":[9,92,101,148,177],"organizes":[10],"clusters":[12,176],"so":[13],"that":[14,63,122],"each":[15,123],"cluster":[16,159,182],"contains":[17,125],"one":[18],"speaker's":[19],"segments.":[20],"This":[21,169],"study":[22],"aims":[23],"to":[24,97,153,180,197],"develop":[25],"online":[26,98],"for":[29,105,166],"multimedia":[30],"retrieval":[32],"on":[33,49,82],"mobile":[34,80],"devices.":[35],"Researchers":[36],"have":[37],"proposed":[38,104,110,165],"various":[39,84],"methods":[40],"of":[41,72,86,117,130,175],"diarization,":[42],"but":[43],"most":[44],"approaches":[45],"thus":[46],"far":[47],"depend":[48],"an":[50,60,118],"empirically":[51],"determined":[52],"threshold":[53],"as":[54,68],"a":[55,127,137,146,187],"criterion":[56,163],"or":[57],"work":[58],"offline":[61],"manner":[62],"requires":[64],"prior":[65],"knowledge,":[66],"such":[67],"the":[69,114,149,172],"overall":[70],"number":[71,129],"speakers.":[73,131],"There":[74],"are":[75,89],"therefore":[76],"clear":[77],"drawbacks":[78],"with":[79,134],"devices,":[81],"which":[83],"types":[85],"frequently":[90],"played":[91],"replaced.":[93],"A":[94,158],"new":[95],"approach":[96,170],"segmentation":[100,111],"clustering":[102],"is":[103,143,151,164],"overcoming":[106],"these":[107],"drawbacks.":[108],"The":[109],"method":[112],"considers":[113],"temporal":[115],"locality":[116],"analysis":[119],"window,":[120],"assuming":[121],"window":[124,147],"only":[126],"small":[128],"In":[132,184],"accordance":[133],"this":[135],"property,":[136],"local":[138],"universal":[139],"background":[140],"model":[141,150],"(UBM)":[142],"constructed":[144],"used":[152],"detect":[154],"points.":[157],"boundary-based":[160],"dynamic":[161],"decision":[162],"clustering.":[168],"estimates":[171],"internal":[173],"characteristics":[174],"uses":[178],"them":[179],"determine":[181],"boundaries.":[183],"experiments":[185],"using":[186],"broadcast":[188],"news":[189],"corpus,":[190],"our":[191],"techniques":[192],"exhibited":[193],"superior":[194],"performance":[195],"compared":[196],"conventional":[198],"approaches.":[199]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}