{"id":"https://openalex.org/W2759592528","doi":"https://doi.org/10.1109/access.2017.2756451","title":"Retrieval of TV Talk-Show Speakers by Associating Audio Transcript to Visual Clusters","display_name":"Retrieval of TV Talk-Show Speakers by Associating Audio Transcript to Visual Clusters","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2759592528","doi":"https://doi.org/10.1109/access.2017.2756451","mag":"2759592528"},"language":"en","primary_location":{"id":"doi:10.1109/access.2017.2756451","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2756451","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2017.2756451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059934834","display_name":"Yina Han","orcid":"https://orcid.org/0000-0001-9713-1821"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yina Han","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9713-1821","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025535689","display_name":"Shanghuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanghuan Song","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100297521","display_name":"Weikang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikang Zhao","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059934834"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13676334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"20512","last_page":"20523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7931720018386841},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7204224467277527},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5670827031135559},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5456037521362305},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5375876426696777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5216991305351257},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49752572178840637},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4381568431854248},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4329044222831726},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4309238791465759},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.43027710914611816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37560224533081055},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3681439161300659},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14673620462417603},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07312214374542236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931720018386841},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7204224467277527},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5670827031135559},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5456037521362305},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5375876426696777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5216991305351257},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49752572178840637},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4381568431854248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4329044222831726},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4309238791465759},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.43027710914611816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37560224533081055},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3681439161300659},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14673620462417603},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07312214374542236},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2017.2756451","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2756451","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c6013ffd6c9d4fdc929a55920235b326","is_oa":true,"landing_page_url":"https://doaj.org/article/c6013ffd6c9d4fdc929a55920235b326","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 5, Pp 20512-20523 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2017.2756451","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2756451","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1612803576","display_name":null,"funder_award_id":"61671388","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8595481553","display_name":null,"funder_award_id":"2016YFC1400200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W802416172","https://openalex.org/W1535144194","https://openalex.org/W1537451167","https://openalex.org/W1550694124","https://openalex.org/W1969198793","https://openalex.org/W1971901154","https://openalex.org/W1990992394","https://openalex.org/W1999227200","https://openalex.org/W2018418896","https://openalex.org/W2030536784","https://openalex.org/W2067191022","https://openalex.org/W2068702980","https://openalex.org/W2080027017","https://openalex.org/W2098973983","https://openalex.org/W2100500227","https://openalex.org/W2100944243","https://openalex.org/W2107558380","https://openalex.org/W2121027212","https://openalex.org/W2132103241","https://openalex.org/W2159011948","https://openalex.org/W2165764569","https://openalex.org/W2168996682","https://openalex.org/W2169772581","https://openalex.org/W2182092229","https://openalex.org/W2250641567","https://openalex.org/W2401989916","https://openalex.org/W2579293819","https://openalex.org/W2620463417","https://openalex.org/W2914885528","https://openalex.org/W3097096317","https://openalex.org/W4310847972","https://openalex.org/W6655310444","https://openalex.org/W6674934066","https://openalex.org/W6675280543","https://openalex.org/W6675529748","https://openalex.org/W6676263510","https://openalex.org/W6683433009","https://openalex.org/W6684860063","https://openalex.org/W6686140342","https://openalex.org/W6691613585","https://openalex.org/W6732147954","https://openalex.org/W6738724077"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Retrieval":[0],"of":[1,14,75,165,194],"TV":[2,34,151],"talk-show":[3,152],"speakers":[4,96],"based":[5],"on":[6,147,170],"solely":[7],"visual":[8,17,39,76,82],"face":[9,184],"recognition":[10],"is":[11,90],"hard":[12],"because":[13],"the":[15,62,69,81,94,111,124,134,166,178,192,195],"significant":[16],"variation":[18],"caused":[19],"by":[20,68,92,122,139,157],"illumination,":[21],"pose,":[22],"size,":[23],"and":[24,42,64,183],"expression,":[25],"which":[26,60,93,123],"can":[27],"exceed":[28],"those":[29,130],"due":[30],"to":[31,72,79,108,129,132],"identity.":[32],"Fortunately,":[33],"talk-shows":[35],"often":[36],"exhibit":[37],"specific":[38,112],"production":[40],"styles":[41],"are":[43,97,126],"accompanied":[44],"with":[45,176],"other":[46],"modalities,":[47],"such":[48],"as":[49],"audio":[50,70],"transcript.":[51],"Hence,":[52],"this":[53],"paper":[54],"presents":[55],"a":[56,73,140],"speaker":[57,86,113,136,180],"retrieval":[58],"framework":[59],"associates":[61],"who":[63,103],"when":[65,133],"information":[66],"provided":[67,156,179],"transcript":[71],"set":[74],"clusters.":[77],"First,":[78],"obtain":[80],"clusters,":[83],"an":[84,119],"unsupervised":[85],"identity":[87],"clustering":[88],"strategy":[89,169],"proposed,":[91],"same":[95],"grouped":[98],"together":[99],"but":[100],"without":[101],"knowing":[102],"exactly":[104],"he/she":[105],"is.":[106],"Then,":[107],"further":[109],"identify":[110],"for":[114],"each":[115],"group,":[116],"we":[117],"propose":[118],"association":[120,168,197],"strategy,":[121],"search":[125],"initially":[127],"limited":[128],"corresponding":[131],"queried":[135],"speaking,":[137],"followed":[138],"graph-based":[141],"densest":[142],"sub-graph":[143],"refinement.":[144],"Comprehensive":[145],"experiments":[146],"3":[148],"h":[149],"French":[150],"\u201cLe":[153],"Grand":[154],"Echiquier\u201d":[155],"K-space":[158],"project":[159],"show":[160],"satisfactory":[161],"results.":[162],"Moreover,":[163],"evaluation":[164],"proposed":[167,196],"more":[171],"challenging":[172],"MediaEval":[173],"2015":[174],"task":[175],"just":[177],"diarization":[181],"module":[182,186],"tracking":[185],"could":[187],"provide":[188],"state-of-the-art":[189],"performances,":[190],"demonstrating":[191],"effect":[193],"strategy.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
